NeurIPS 2024 Papers

Foundation models have emerged as powerful tools across various domains including language, vision, and multimodal tasks. While prior works have addressed unsupervised semantic segmentation, they significantly lag behind supervised models. In this paper, we use a diffusion UNet encoder as a foundation vision encoder and introduce DiffCut, an unsupervised zero-shot segmentation method that solely harnesses the output features from the final self-attention block. Through extensive experimentation, we demonstrate that using these diffusion features in a graph based segmentation algorithm, significantly outperforms previous state-of-the-art methods on zero-shot segmentation. Specifically, we leverage a recursive Normalized Cut algorithm that regulates the granularity of detected objects and produces well-defined segmentation maps that precisely capture intricate image details. Our work highlights the remarkably accurate semantic knowledge embedded within diffusion UNet encoders that could then serve as foundation vision encoders for downstream tasks.

This paper explores the weakly-supervised referring image segmentation (WRIS) problem, and focuses on a challenging setup where target localization is learned directly from image-text pairs. We note that the input text description typically already contains detailed information on how to localize the target object, and we also observe that humans often follow a step-by-step comprehension process (\ie, progressively utilizing target-related attributes and relations as cues) to identify the target object. Hence, we propose a novel Progressive Comprehension Network (PCNet) to leverage target-related textual cues from the input description for progressively localizing the target object. Specifically, we first use a Large Language Model (LLM) to decompose the input text description into short phrases. These short phrases are taken as target-related cues and fed into a Conditional Referring Module (CRM) in multiple stages, to allow updating the referring text embedding and enhance the response map for target localization in a multi-stage manner. Based on the CRM, we then propose a Region-aware Shrinking (RaS) loss to constrain the visual localization to be conducted progressively in a coarse-to-fine manner across different stages. Finally, we introduce an Instance-aware Disambiguation (IaD) loss to suppress instance localization ambiguity by differentiating overlapping response maps generated by different referring texts on the same image. Extensive experiments show that our method outperforms SOTA methods on three common benchmarks.

We present LRM-Zero, a Large Reconstruction Model (LRM) trained entirely on synthesized 3D data, achieving high-quality sparse-view 3D reconstruction. The core of LRM-Zero is our procedural 3D dataset, Zeroverse, which is automatically synthesized from simple primitive shapes with random texturing and augmentations (e.g., height fields, boolean differences, and wireframes). Unlike previous 3D datasets (e.g., Objaverse) which are often captured or crafted by humans to approximate real 3D data, Zeroverse completely ignores realistic global semantics but is rich in complex geometric and texture details that are locally similar to or even more intricate than real objects. We demonstrate that our LRM-Zero, trained with our fully synthesized Zeroverse, can achieve high visual quality in the reconstruction of real-world objects, competitive with models trained on Objaverse. We also analyze several critical design choices of Zeroverse that contribute to LRM-Zero's capability and training stability. Our work demonstrates that 3D reconstruction, one of the core tasks in 3D vision, can potentially be addressed without the semantics of real-world objects. The Zeroverse's procedural synthesis code and interactive visualization are available at: https://desaixie.github.io/lrm-zero/.

Domain generalization (DG) is a fundamental yet challenging topic in machine learning. Recently, the remarkable zero-shot capabilities of the large pre-trained vision-language model (e.g., CLIP) have made it popular for various downstream tasks. However, the effectiveness of this capacity often degrades when there are shifts in data distribution during testing compared to the training data. In this paper, we propose a novel method, known as CLIPCEIL, a model that utilizes Channel rEfinement and Image-text aLignment to facilitate the CLIP to the inaccessible $\textit{out-of-distribution}$ test datasets that exhibit domain shifts. Specifically, we refine the feature channels in the visual domain to ensure they contain domain-invariant and class-relevant features by using a lightweight adapter. This is achieved by minimizing the inter-domain variance while maximizing the inter-class variance. In the meantime, we ensure the image-text alignment by aligning text embeddings of the class descriptions and their corresponding image embedding while further removing the domain-specific features. Moreover, our model integrates multi-scale CLIP features by utilizing a self-attention fusion module, technically implemented through one Transformer layer. Extensive experiments on five widely used benchmark datasets demonstrate that CLIPCEIL outperforms the existing state-of-the-art methods. The source code is available at \url{https://github.com/yuxi120407/CLIPCEIL}.

In this paper, we introduce YOLA, a novel framework for object detection in low-light scenarios. Unlike previous works, we propose to tackle this challenging problem from the perspective of feature learning. Specifically, we propose to learn illumination-invariant features through the Lambertian image formation model. We observe that, under the Lambertian assumption, it is feasible to approximate illumination-invariant feature maps by exploiting the interrelationships between neighboring color channels and spatially adjacent pixels. By incorporating additional constraints, these relationships can be characterized in the form of convolutional kernels, which can be trained in a detection-driven manner within a network. Towards this end, we introduce a novel module dedicated to the extraction of illumination-invariant features from low-light images, which can be easily integrated into existing object detection frameworks. Our empirical findings reveal significant improvements in low-light object detection tasks, as well as promising results in both well-lit and over-lit scenarios.

As an emerging task that integrates perception and reasoning, topology reasoning in autonomous driving scenes has recently garnered widespread attention. However, existing work often emphasizes "perception over reasoning": they typically boost reasoning performance by enhancing the perception of lanes and directly adopt vanilla MLPs to learn lane topology from lane query. This paradigm overlooks the geometric features intrinsic to the lanes themselves and are prone to being influenced by inherent endpoint shifts in lane detection. To tackle this issue, we propose an interpretable method for lane topology reasoning based on lane geometric distance and lane query similarity, named TopoLogic. This method mitigates the impact of endpoint shifts in geometric space, and introduces explicit similarity calculation in semantic space as a complement. By integrating results from both spaces, our methods provides more comprehensive information for lane topology. Ultimately, our approach significantly outperforms the existing state-of-the-art methods on the mainstream benchmark OpenLane-V2 (23.9 v.s. 10.9 in TOP$_{ll}$ and 44.1 v.s. 39.8 in OLS on subsetA). Additionally, our proposed geometric distance topology reasoning method can be incorporated into well-trained models without re-training, significantly enhancing the performance of lane topology reasoning. The code is released at https://github.com/Franpin/TopoLogic.

No-Reference Point Cloud Quality Assessment (NR-PCQA) aims to objectively assess the human perceptual quality of point clouds without relying on pristine-quality point clouds for reference. It is becoming increasingly significant with the rapid advancement of immersive media applications such as virtual reality (VR) and augmented reality (AR). However, current NR-PCQA models attempt to indiscriminately learn point cloud content and distortion representations within a single network, overlooking their distinct contributions to quality information. To address this issue, we propose DisPA, a novel disentangled representation learning framework for NR-PCQA. The framework trains a dual-branch disentanglement network to minimize mutual information (MI) between representations of point cloud content and distortion. Specifically, to fully disentangle representations, the two branches adopt different philosophies: the content-aware encoder is pretrained by a masked auto-encoding strategy, which can allow the encoder to capture semantic information from rendered images of distorted point clouds; the distortion-aware encoder takes a mini-patch map as input, which forces the encoder to focus on low-level distortion patterns. Furthermore, we utilize an MI estimator to estimate the tight upper bound of the actual MI and further minimize it to achieve explicit representation disentanglement. Extensive experimental results demonstrate that DisPA outperforms state-of-the-art methods on multiple PCQA datasets.

Fine-grained visual classification (FGVC) involves classifying closely related subcategories. This task is inherently difficult due to the subtle differences between classes and the high intra-class variance. Moreover, FGVC datasets are typically small and challenging to gather, thus highlighting a significant need for effective data augmentation. Recent advancements in text-to-image diffusion models have introduced new possibilities for data augmentation in image classification. While these models have been used to generate training data for classification tasks, their effectiveness in full-dataset training of FGVC models remains under-explored. Recent techniques that rely on text-to-image generation or Img2Img methods, such as SDEdit, often struggle to generate images that accurately represent the class while modifying them to a degree that significantly increases the dataset's diversity. To address these challenges, we present SaSPA: Structure and Subject Preserving Augmentation. Contrary to recent methods, our method does not use real images as guidance, thereby increasing generation flexibility and promoting greater diversity. To ensure accurate class representation, we employ conditioning mechanisms, specifically by conditioning on image edges and subject representation. We conduct extensive experiments and benchmark SaSPA against both traditional and generative data augmentation techniques. SaSPA consistently outperforms all established baselines across multiple settings, including full dataset training and contextual bias. Additionally, our results reveal interesting patterns in using synthetic data for FGVC models; for instance, we find a relationship between the amount of real data used and the optimal proportion of synthetic data.

Indoor radar perception has seen rising interest due to affordable costs driven by emerging automotive imaging radar developments and the benefits of reduced privacy concerns and reliability under hazardous conditions (e.g., fire and smoke). However, existing radar perception pipelines fail to account for distinctive characteristics of the multi-view radar setting. In this paper, we propose Radar dEtection TRansformer (RETR), an extension of the popular DETR architecture, tailored for multi-view radar perception. RETR inherits the advantages of DETR, eliminating the need for hand-crafted components for object detection and segmentation in the image plane. More importantly, RETR incorporates carefully designed modifications such as 1) depth-prioritized feature similarity via a tunable positional encoding (TPE); 2) a tri-plane loss from both radar and camera coordinates; and 3) a learnable radar-to-camera transformation via reparameterization, to account for the unique multi-view radar setting. Evaluated on two indoor radar perception datasets, our approach outperforms existing state-of-the-art methods by a margin of 15.38+ AP for object detection and 11.91+ IoU for instance segmentation, respectively. Our implementation is available at https://github.com/merlresearch/radar-detection-transformer.

We study the problem of estimating the body movements of a camera wearer from egocentric videos. Current methods for ego-body pose estimation rely on temporally dense sensor data, such as IMU measurements from spatially sparse body parts like the head and hands. However, we propose that even temporally sparse observations, such as hand poses captured intermittently from egocentric videos during natural or periodic hand movements, can effectively constrain overall body motion. Naively applying diffusion models to generate full-body pose from head pose and sparse hand pose leads to suboptimal results. To overcome this, we develop a two-stage approach that decomposes the problem into temporal completion and spatial completion. First, our method employs masked autoencoders to impute hand trajectories by leveraging the spatiotemporal correlations between the head pose sequence and intermittent hand poses, providing uncertainty estimates. Subsequently, we employ conditional diffusion models to generate plausible full-body motions based on these temporally dense trajectories of the head and hands, guided by the uncertainty estimates from the imputation. The effectiveness of our methods was rigorously tested and validated through comprehensive experiments conducted on various HMD setup with AMASS and Ego-Exo4D datasets. Project page: https://sgchi.github.io/dsposer

Federated Learning (FL) allows multiple clients to collaboratively train models without directly sharing their private data. While various data augmentation techniques have been actively studied in the FL environment, most of these methods share input-level or feature-level data information over communication, posing potential privacy leakage. In response to this challenge, we introduce a federated data augmentation algorithm named FedAvP that shares only the augmentation policies, not the data-related information. For data security and efficient policy search, we interpret the policy loss as a meta update loss in standard FL algorithms and utilize the first-order gradient information to further enhance privacy and reduce communication costs. Moreover, we propose a meta-learning method to search for adaptive personalized policies tailored to heterogeneous clients. Our approach outperforms existing best performing augmentation policy search methods and federated data augmentation methods, in the benchmarks for heterogeneous FL.

Modality differences have led to the development of heterogeneous architectures for vision and language models. While images typically require 2D non-causal modeling, texts utilize 1D causal modeling. This distinction poses significant challenges in constructing unified multi-modal models. This paper explores the feasibility of representing images using 1D causal modeling. We identify an "over-focus" issue in existing 1D causal vision models, where attention overly concentrates on a small proportion of visual tokens. The issue of "over-focus" hinders the model's ability to extract diverse visual features and to receive effective gradients for optimization. To address this, we propose De-focus Attention Networks, which employ learnable bandpass filters to create varied attention patterns. During training, large and scheduled drop path rates, and an auxiliary loss on globally pooled features for global understanding tasks are introduced. These two strategies encourage the model to attend to a broader range of tokens and enhance network optimization. Extensive experiments validate the efficacy of our approach, demonstrating that 1D causal visual representation can perform comparably to 2D non-causal representation in tasks such as global perception, dense prediction, and multi-modal understanding. Code shall be released.

We present PiMForce, a novel framework that enhances hand pressure estimation by leveraging 3D hand posture information to augment forearm surface electromyography (sEMG) signals. Our approach utilizes detailed spatial information from 3D hand poses in conjunction with dynamic muscle activity from sEMG to enable accurate and robust whole-hand pressure measurements under diverse hand-object interactions. We also developed a multimodal data collection system that combines a pressure glove, an sEMG armband, and a markerless finger-tracking module. We created a comprehensive dataset from 21 participants, capturing synchronized data of hand posture, sEMG signals, and exerted hand pressure across various hand postures and hand-object interaction scenarios using our collection system. Our framework enables precise hand pressure estimation in complex and natural interaction scenarios. Our approach substantially mitigates the limitations of traditional sEMG-based or vision-based methods by integrating 3D hand posture information with sEMG signals. Video demos, data, and code are available online.

LiDAR point cloud semantic segmentation enables the robots to obtain fine-grained semantic information of the surrounding environment. Recently, many works project the point cloud onto the 2D image and adopt the 2D Convolutional Neural Networks (CNNs) or vision transformer for LiDAR point cloud semantic segmentation. However, since more than one point can be projected onto the same 2D position but only one point can be preserved, the previous 2D projection-based segmentation methods suffer from inevitable quantized information loss, which results in incomplete geometric structure, especially for small objects. To avoid quantized information loss, in this paper, we propose a novel spherical frustum structure, which preserves all points projected onto the same 2D position. Additionally, a hash-based representation is proposed for memory-efficient spherical frustum storage. Based on the spherical frustum structure, the Spherical Frustum sparse Convolution (SFC) and Frustum Farthest Point Sampling (F2PS) are proposed to convolve and sample the points stored in spherical frustums respectively. Finally, we present the Spherical Frustum sparse Convolution Network (SFCNet) to adopt 2D CNNs for LiDAR point cloud semantic segmentation without quantized information loss. Extensive experiments on the SemanticKITTI and nuScenes datasets demonstrate that our SFCNet outperforms previous 2D projection-based semantic segmentation methods based on conventional spherical projection and shows better performance on small object segmentation by preserving complete geometric structure. Codes will be available at https://github.com/IRMVLab/SFCNet.

Human visual search ability enables efficient and accurate tracking of an arbitrary moving target, which is a significant research interest in cognitive neuroscience. The recently proposed Central-Peripheral Dichotomy (CPD) theory sheds light on how humans effectively process visual information and track moving targets in complex environments. However, existing visual object tracking algorithms still fall short of matching human performance in maintaining tracking over time, particularly in complex scenarios requiring robust visual search skills. These scenarios often involve Spatio-Temporal Discontinuities (i.e., STDChallenge), prevalent in long-term tracking and global instance tracking. To address this issue, we conduct research from a human-like modeling perspective: (1) Inspired by the CPD, we pro- pose a new tracker named CPDTrack to achieve human-like visual search ability. The central vision of CPDTrack leverages the spatio-temporal continuity of videos to introduce priors and enhance localization precision, while the peripheral vision improves global awareness and detects object movements. (2) To further evaluate and analyze STDChallenge, we create the STDChallenge Benchmark. Besides, by incorporating human subjects, we establish a human baseline, creating a high- quality environment specifically designed to assess trackers’ visual search abilities in videos across STDChallenge. (3) Our extensive experiments demonstrate that the proposed CPDTrack not only achieves state-of-the-art (SOTA) performance in this challenge but also narrows the behavioral differences with humans. Additionally, CPDTrack exhibits strong generalizability across various challenging benchmarks. In summary, our research underscores the importance of human-like modeling and offers strategic insights for advancing intelligent visual target tracking. Code and models are available at https://github.com/ZhangDailing8/CPDTrack.

While Large Language Models (LLMs) have become immensely popular due to their outstanding performance on a broad range of tasks, these models are prone to producing hallucinations— outputs that are fallacious or fabricated yet often appear plausible or tenable at a glance. In this paper, we conduct a comprehensive investigation into the nature of hallucinations within LLMs and furthermore explore effective techniques for detecting such inaccuracies in various real-world settings. Prior approaches to detect hallucinations in LLM outputs, such as consistency checks or retrieval-based methods, typically assume access to multiple model responses or large databases. These techniques, however, tend to be computationally expensive in practice, thereby limiting their applicability to real-time analysis. In contrast, in this work, we seek to identify hallucinations within a single response in both white-box and black-box settings by analyzing the internal hidden states, attention maps, and output prediction probabilities of an auxiliary LLM. In addition, we also study hallucination detection in scenarios where ground-truth references are also available, such as in the setting of Retrieval-Augmented Generation (RAG). We demonstrate that the proposed detection methods are extremely compute-efficient, with speedups of up to 45x and 450x over other baselines, while achieving significant improvements in detection performance over diverse datasets.

Binary analysis is a core component of many critical security tasks, including reverse engineering, malware analysis, and vulnerability detection. Manual analysis is often time-consuming, but identifying commonly-used or previously-seen functions can reduce the time it takes to understand a new file. However, given the complexity of assembly, and the NP-hard nature of determining function equivalence, this task is extremely difficult. Common approaches often use sophisticated disassembly and decompilation tools, graph analysis, and other expensive pre-processing steps to perform function similarity searches over some corpus. In this work, we identify a number of discrepancies between the current research environment and the underlying application need. To remedy this, we build a new benchmark, REFuSe-Bench, for binary function similarity detection consisting of high-quality datasets and tests that better reflect real-world use cases. In doing so, we address issues like data duplication and accurate labeling, experiment with real malware, and perform the first serious evaluation of ML binary function similarity models on Windows data. Our benchmark reveals that a new, simple baseline — one which looks at only the raw bytes of a function, and requires no disassembly or other pre-processing --- is able to achieve state-of-the-art performance in multiple settings. Our findings challenge conventional assumptions that complex models with highly-engineered features are being used to their full potential, and demonstrate that simpler approaches can provide significant value.

Point Cloud Interpolation confronts challenges from point sparsity, complex spatiotemporal dynamics, and the difficulty of deriving complete 3D point clouds from sparse temporal information. This paper presents NeuroGauss4D-PCI, which excels at modeling complex non-rigid deformations across varied dynamic scenes. The method begins with an iterative Gaussian cloud soft clustering module, offering structured temporal point cloud representations. The proposed temporal radial basis function Gaussian residual utilizes Gaussian parameter interpolation over time, enabling smooth parameter transitions and capturing temporal residuals of Gaussian distributions. Additionally, a 4D Gaussian deformation field tracks the evolution of these parameters, creating continuous spatiotemporal deformation fields. A 4D neural field transforms low-dimensional spatiotemporal coordinates ($x,y,z,t$) into a high-dimensional latent space. Finally, we adaptively and efficiently fuse the latent features from neural fields and the geometric features from Gaussian deformation fields. NeuroGauss4D-PCI outperforms existing methods in point cloud frame interpolation, delivering leading performance on both object-level (DHB) and large-scale autonomous driving datasets (NL-Drive), with scalability to auto-labeling and point cloud densification tasks.

Accurate estimation of human pose and the pose of interacting objects, like a hockey stick, is crucial for action recognition and performance analysis, particularly in sports. Existing methods capture the object along with the human in the bounding boxes, assuming all keypoints are visible within the bounding box. This necessitates larger bounding boxes to capture the object, introducing unnecessary visual features and hindering performance in real-world cluttered environments. We propose a simple image and text-based multimodal solution TokenCLIPose that addresses this limitation. Our approach focuses solely on human keypoints within the bounding box, treating objects as unseen. TokenCLIPose leverages the rich semantic representations endowed by language for inducing keypoint-specific context, even for occluded keypoints. We evaluate the performance of TokenCLIPose on a real-world Ice-Hockey dataset, and demonstrate its generalizability through zero-shot transfer to a smaller Lacrosse dataset. Additionally, we showcase its flexibility on CrowdPose, a popular occlusion benchmark with keypoints within the bounding box. Our method significantly improves over state-of-the-art approaches on all three datasets, with gains of 4.36\%, 2.35\%, and 3.8\%, respectively.