ECCV 2024 Papers

"Scaling up the size of vision models has been the de facto standard to obtain more powerful visual representations. In this work, we discuss the point beyond which larger vision models are not necessary. First, we demonstrate the power of Scaling on Scales (), whereby a pre-trained and frozen smaller vision model (, ViT-B or ViT-L), run over multiple image scales, can outperform larger models (, ViT-H or ViT-G) on classification, segmentation, depth estimation, Multimodal LLM (MLLM) benchmarks, and robotic manipulation. Notably, achieves state-of-the-art performance in detailed understanding of MLLM on the V∗ benchmark, surpassing models such as GPT-4V. We examine the conditions under which is a preferred scaling approach compared to scaling on model size. While larger models have the advantage of better generalization on hard examples, we show that features of larger vision models can be well approximated by those of multi-scale smaller models. This suggests most, if not all, of the representations learned by current large pre-trained models can also be obtained from multi-scale smaller models. Our results show that a multi-scale smaller model has comparable learning capacity to a larger model, and pre-training smaller models with can match or even exceed the advantage of larger models. We release a Python package that can apply on any vision model with one line of code: https://github.com/bfshi/scaling_on_scales."

"Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliability of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an effort to avoid erroneous pseudo-labels. However, high confidence does not guarantee correct pseudo-labels especially in the initial training iterations. In this paper, we propose a novel approach to reliably learn from pseudo-labels. First, we unify the predictions from a trained object detector and a semantic segmentation model to identify reliable pseudo-label pixels. Second, we assign different learning weights to pseudo-labeled pixels to avoid noisy training signals. To determine these weights, we first use the reliable pseudo-label pixels identified from the first step and labeled pixels to construct a prototype for each class. Then, the per-pixel weight is the similarity score between the pixel and the prototype measured via rank-statistics. This metric is robust to noise, making it better suited for comparing features from unlabeled images, particularly in the initial training phases where wrong pseudo labels are prone to occur. We show that our method can be easily integrated into four semi-supervised semantic segmentation frameworks, and improves them in both Cityscapes and Pascal VOC datasets. Code is available at https://github.com/cvlab-stonybrook/ Weighting-Pseudo-Labels."

"In this work, we study the problem of continual learning (CL) where the goal is to learn a model on a sequence of tasks, under the assumption that the data from the previous tasks becomes unavailable while learning on the current task data. CL is essentially a balancing act between learning on the new task (plasticity) and maintaining the performance on the previously learned concepts (stability). To address the stability-plasticity trade-off, we propose to perform weight-ensembling of the model parameters of the previous and current tasks. This weighted-ensembled model, which we call Continual Model Averaging (or CoMA), attains high accuracy on the current task by leveraging plasticity, while not deviating too far from the previous weight configuration, ensuring stability. We also propose an improved variant of CoMA, named Continual Fisher-weighted Model Averaging (or CoFiMA), that selectively weighs each parameter in the weights ensemble by leveraging the Fisher information of the weights of the model. Both variants are conceptually simple, easy to implement, and effective in attaining state-of-the-art performance on several standard CL benchmarks. Code is available at: https://github.com/IemProg/CoFiMA."

"In this article, we introduce a novel normalization technique for neural network weight matrices, which we term weight conditioning. This approach aims to narrow the gap between the smallest and largest singular values of the weight matrices, resulting in better-conditioned matrices. The inspiration for this technique partially derives from numerical linear algebra, where well-conditioned matrices are known to facilitate stronger convergence results for iterative solvers. We provide a theoretical foundation demonstrating that our normalization technique smoothens the loss landscape, thereby enhancing convergence of stochastic gradient descent algorithms. Empirically, we validate our normalization across various neural network architectures, including Convolutional Neural Networks (CNNs), Vision Transformers (ViT), Neural Radiance Fields (NeRF), and 3D shape modeling. Our findings indicate that our normalization method is not only competitive but also outperforms existing weight normalization techniques from the literature."

"In the era of content creation revolution propelled by advancements in generative models, the field of web design remains unexplored despite its critical role in modern digital communication. The web design process is complex and often time-consuming, especially for those with limited expertise. In this paper, we introduce Web Rendering Parameters Generation (WebRPG), a new task that aims at automating the generation for visual presentation of web pages based on their HTML code. WebRPG would contribute to a faster web development workflow. Since there is no existing benchmark available, we develop a new dataset for WebRPG through an automated pipeline. Moreover, we present baseline models, utilizing VAE to manage numerous elements and rendering parameters, along with custom HTML embedding for capturing essential semantic and hierarchical information from HTML. Extensive experiments, including customized quantitative evaluations for this specific task, are conducted to evaluate the quality of the generated results. The dataset and code can be accessed at GitHub1 . 1 https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/ DocumentUnderstanding/WebRPG"

"This paper introduces a novel framework for virtual try-on, termed . Different from previous methods, is a customizable solution. Besides generating high-fidelity results, our method supports users to precisely manipulate the wearing style. To achieve this goal, we first construct a strong pipeline for standard virtual try-on, supporting single/multiple garment try-on and model-to-model settings in complicated scenarios. To make it manipulable, we propose sparse correspondence alignment which involves point-based control to guide the generation for specific locations. With this design, Wear-Any-Way gets state-of-the-art performance for the standard setting and provides a novel interaction form for customizing the wearing style. For instance, it supports users to drag the sleeve to make it rolled up, drag the coat to make it open, and utilize clicks to control the style of tuck, etc. enables more liberated and flexible expressions of the attires, holding profound implications in the fashion industry. Project page is mengtingchen.github.io/wear-any-way-page."

"The ground-to-satellite image matching/retrieval was initially proposed for city-scale ground camera localization. This work addresses the problem of improving camera pose accuracy by ground-to-satellite image matching after a coarse location and orientation have been obtained, either from the city-scale retrieval or from consumer-level GPS and compass sensors. Existing learning-based methods for solving this task require accurate GPS labels of ground images for network training. However, obtaining such accurate GPS labels is difficult, often requiring an expensive blackReal Time Kinematics (RTK) setup and suffering from signal occlusion, multi-path signal disruptions, . To alleviate this issue, this paper proposes a weakly supervised learning strategy for ground-to-satellite image registration when only noisy pose labels for ground images are available for network training. It derives positive and negative satellite images for each ground image and leverages contrastive learning to learn feature representations for ground and satellite images useful for translation estimation. We also propose a self-supervision strategy for cross-view image relative rotation estimation, which trains the network by creating pseudo query and reference image pairs. Experimental results show that our weakly supervised learning strategy achieves the best performance on cross-area evaluation compared to recent state-of-the-art methods that are reliant on accurate pose labels for supervision."

"This paper explores the spatio-temporal video grounding (STVG) task, which aims at localizing a particular object corresponding to a given textual description in an untrimmed video. Existing approaches mainly resort to object-level manual annotations as the supervision for addressing this challenging task. Such a paradigm heavily constrains the scalability of processing large-scale unlabeled data. To this end, we present a novel framework that is capable of grounding the target object relying only on the video-sentence correspondence. Specifically, our model re-formulates the original STVG task as two cross-modal alignment sub-problems: region-phrase and frame-sentence. Since the absence of ground-truth alignments during the training stage, we treat them as latent variables and learn to model the joint conditional distribution by reconstructing the interactions of entities in the video. The entire framework can be effectively optimized by the variational Expectation-Maximization (EM) algorithm, which alternates between two updating steps for progressively maximizing the likelihood of query sentence, thereby approximating the real cross-modal assignment. Extensive experiments on two video benchmarks (VidSTG and HC-STVG) further show the effectiveness of the proposed method."

"Fully-supervised monocular 3D hand reconstruction is often difficult because capturing the requisite 3D data entails deploying specialized equipment in a controlled environment. We introduce a weakly-supervised method that avoids such requirements by leveraging fundamental principles well-established in the understanding of the human hand’s unique structure and functionality. Specifically, we systematically study hand knowledge from different sources, including biomechanics, functional anatomy, and physics. We effectively incorporate these valuable foundational insights into 3D hand reconstruction models through an appropriate set of differentiable training losses. This enables training solely with readily-obtainable 2D hand landmark annotations and eliminates the need for expensive 3D supervision. Moreover, we explicitly model the uncertainty that is inherent in image observations. We enhance the training process by exploiting a simple yet effective Negative Log-Likelihood (NLL) loss that incorporates uncertainty into the loss function. Through extensive experiments, we demonstrate that our method significantly outperforms state-of-the-art weakly-supervised methods. For example, our method achieves nearly a 21% performance improvement on the widely adopted FreiHAND dataset."

"Class activation maps (CAMs) are commonly employed in weakly supervised semantic segmentation (WSSS) to produce pseudo-labels. Due to incomplete or excessive class activation, existing studies often resort to offline CAM refinement, introducing additional stages or proposing offline modules. This can cause optimization difficulties for single-stage methods and limit generalizability. In this study, we aim to reduce the observed CAM inconsistency and error to mitigate reliance on refinement processes. We propose an end-to-end WSSS model incorporating guided CAMs, wherein our segmentation model is trained while concurrently optimizing CAMs online. Our method, Co-training with Swapping Assignments (CoSA), leverages a dual-stream framework, where one sub-network learns from the swapped assignments generated by the other. We introduce three techniques in this framework: i) soft perplexity-based regularization to penalize uncertain regions; ii) a threshold-searching approach to dynamically revise the confidence threshold; and iii) contrastive separation to address the coexistence problem. CoSA demonstrates exceptional performance, achieving mIoU of 76.2% and 51.0% on VOC and COCO validation datasets, respectively, surpassing existing baselines by a substantial margin. Notably, CoSA is the first single-stage approach to outperform all existing multi-stage methods including those with additional supervision. Source code is publicly available here."

"Weakly supervised 3D object detection aims to learn a 3D detector with lower annotation cost, e.g., 2D labels. Unlike prior work which still relies on few accurate 3D annotations, we propose a framework to study how to leverage constraints between 2D and 3D domains without requiring any 3D labels. Specifically, we employ visual data from three perspectives to establish connections between 2D and 3D domains. First, we design a feature-level constraint to align LiDAR and image features based on object-aware regions. Second, the output-level constraint is developed to enforce the overlap between 2D and projected 3D box estimations. Finally, the training-level constraint is utilized by producing accurate and consistent 3D pseudo-labels that align with the visual data. We conduct extensive experiments on the KITTI dataset to validate the effectiveness of the proposed three constraints. Without using any 3D labels, our method achieves favorable performance against state-of-the-art approaches and is competitive with the method that uses 500-frame 3D annotations. Code and models will be made publicly available."

"Vision-language (VL) models often exhibit a limited understanding of complex expressions of visual objects (, attributes, shapes, and their relations), given complex and diverse language queries. Traditional approaches attempt to improve VL models using hard negative synthetic text, but their effectiveness is limited. In this paper, we harness the exceptional compositional understanding capabilities of generative foundational models. We introduce a novel method for structured synthetic data generation aimed at enhancing the compositional understanding of VL models in language-based object detection. Our framework generates densely paired positive and negative triplets (image, text descriptions, and bounding boxes) in both image and text domains. By leveraging these synthetic triplets, we transform ‘weaker’ VL models into ‘stronger’ models in terms of compositional understanding, a process we call “Weak-to-Strong Compositional Learning” (WSCL). To achieve this, we propose a new compositional contrastive learning formulation that discovers semantics and structures in complex descriptions from synthetic triplets. As a result, VL models trained with our synthetic data generation exhibit a significant performance boost in the Omnilabel benchmark by up to +5AP and the D3 benchmark by +6.9AP upon existing baselines."

"Transcription-only Supervised Text Spotting aims to learn text spotters relying only on transcriptions but no text boundaries for supervision, thus eliminating expensive boundary annotation. The crux of this task lies in locating each transcription in scene text images without location annotations. In this work, we formulate this challenging problem as a Weakly Supervised Cross-modality Contrastive Learning problem, and design a simple yet effective model dubbed that is able to detect each transcription in a scene image in a weakly supervised manner. Unlike typical methods for cross-modality contrastive learning that focus on modeling the holistic semantic correlation between an entire image and a text description, our conducts atomistic contrastive learning to model the character-wise appearance consistency between a text transcription and its correlated region in a scene image to detect an anchor point for the transcription in a weakly supervised manner. The detected anchor points by are further used as pseudo location labels to guide the learning of text spotting. Extensive experiments on four challenging benchmarks demonstrate the superior performance of our model over other methods. Code will be released."

"Recently learned image compression (LIC) has achieved great progress and even outperformed the traditional approach using DCT or discrete wavelet transform (DWT). However, LIC mainly reduces spatial redundancy in the autoencoder networks and entropy coding, but has not fully removed the frequency-domain correlation explicitly as in DCT or DWT. To leverage the best of both worlds, we propose a surprisingly simple but efficient framework, which introduces the DWT to both the convolution layers and entropy coding of CNN-based LIC. First, in both the core and hyperprior autoencoder networks, we propose a Wavelet-domain Convolution (WeConv) module, which performs convolution after DWT, and then converts the data back to spatial domain via inverse DWT. This module is used at selected layers in a CNN network to reduce the frequency-domain correlation explicitly and make the signal sparser in DWT domain. We also propose a Wavelet-domain Channel-wise Auto-Regressive entropy Model (WeChARM), where the output latent representations from the encoder network are first transformed by the DWT, before applying quantization and entropy coding, as in the traditional paradigm. Moreover, the entropy coding is split into two steps. We first code all low-frequency DWT coefficients, and then use them as prior to code high-frequency coefficients. The channel-wise entropy coding is further used in each step. By combining WeConv and WeChARM, the proposed WeConvene scheme achieves superior R-D performance compared to other state-of-the-art LIC methods as well as the latest H.266/VVC. For the Kodak dataset and the baseline network with −0.4% BD-Rate saving over H.266/VVC, introducing WeConv with the simplest Haar transform improves the saving to −4.7%. This is quite impressive given the simplicity of the Haar transform. Enabling Haar-based WeChARM entropy coding further boosts the saving to −8.2%. When the Haar transform is replaced by the 5/3 or 9/7 wavelet, the overall saving becomes −9.4% and −9.8% respectively. The standalone WeConv layer can also be used in many other computer vision tasks beyond image/video compression. The source code is available at https: //github.com/fengyurenpingsheng/WeConvene."

./abstract

"Spectral imaging offers the capability to unveil hidden details within the world around us. However, to fully harness this potential, it is imperative to develop effective spectral demosaicing techniques. Despite the success of learning based spectral demosaicing methods, three challenges hinder their practical use. Firstly, existing convolutional neural networks and attention-based models, struggle to capture spectral similarities and long-range dependencies. Secondly, their performance is unstable when optical characteristics, like multispectral filter array (MSFA) arrangement and wavelength distribution, change. Lastly, they lack a structured approach to incorporating imaging system physics, such as MSFA pattern. Addressing these challenges, our paper introduces the Wavelength Embedding guided Filter Array Attention Transformer (WeFAT) for effective spectral demosaicing. Specifically, inspired by the timestep embedding in denoising diffusion models, we propose a Wavelength Embedding guided Multi-head Self-Attention (We-MSA) mechanism to imbue our model with wavelength memory, facilitating adaptation to diverse cameras. This approach treats each spectral feature as a token, directly integrating wavelength information into attention calculation. Additionally, we developed a MSFA-attention Mechanism (MaM) steering We-MSA to focus on spatial regions yielding high-quality spectral data. Experimental results affirm that WeFAT exhibits strong performance consistency across diverse cameras characterized by varying spectral distributions and MSFA patterns, trained solely on ARAD dataset. It also outperforms current state-of-the-art methods in both simulated and real datasets."

"Low illumination significantly impacts the performance of learning-based models trained under well-lit conditions. While current methods mitigate this issue through either image-level enhancement or feature-level adaptation, they often focus solely on the image itself, ignoring how the task-relevant target varies along with different illumination. In this paper, we propose a target-aware representation learning framework designed to improve high-level task performance in low-illumination environments. We achieve a bi-directional domain alignment from both image appearance and semantic features to bridge data across different illumination conditions. To concentrate more effectively on the target, we design a target highlighting strategy, incorporated with the saliency mechanism and Temporal Gaussian Mixture Model to emphasize the location and movement of task-relevant targets. We also design a mask token-based representation learning scheme to learn a more robust target-aware feature. Our framework ensures compact and effective feature representation for high-level vision tasks in low-lit settings. Extensive experiments conducted on CODaN, ExDark, and ARID datasets validate the effectiveness of our approach for a variety of image and video-based tasks, including classification, detection, and action recognition. Our code is available at https://github.com/ZhangYh994/WiiD."

"The success of denoising diffusion models in generating and editing images has sparked interest in using diffusion models for editing 3D scenes represented via neural radiance fields (NeRFs). However, current 3D editing methods lack a way to both pinpoint the edit location and limit changes to the desired volumetric region. Consequently, these methods often over-edit, altering irrelevant parts of the scene. We introduce a new task, 3D edit localization, to automatically identify the relevant region for an editing task and restrict the edit accordingly. To achieve this goal, we initially tackle 2D edit localization, and then lift it to multiple views to address the 3D localization challenge. For 2D localization, we leverage InstructPix2Pix (IP2P) and identify the discrepancy between IP2P predictions with and without the instruction. We refer to this discrepancy as the relevance map. The relevance map conveys the importance of changing each pixel to achieve an edit, and guides downstream modifications, ensuring that pixels irrelevant to the edit remain unchanged. With the relevance maps of multiview posed images, we can define the relevance field, defining the 3D region within which modifications should be made. This enables us to improve the quality of text-guided 3D NeRF scene editing, by performing iterative updates on the training views, guided by renders from the relevance field. Our method achieves state-of-the-art performance on both NeRF and image editing tasks. We will make the code available."

"The supervision of state-of-the-art multiple object tracking (MOT) methods requires enormous annotation efforts to provide bounding boxes for all frames of all videos, and instance IDs to associate them through time. To this end, we introduce Walker, the first self-supervised tracker that learns from videos with sparse bounding box annotations, and no tracking labels. First, we design a quasi-dense temporal object appearance graph, and propose a novel multi-positive contrastive objective to optimize random walks on the graph and learn instance similarities. Then, we introduce an algorithm to enforce mutually-exclusive connective properties across instances in the graph, optimizing the learned topology for MOT. At inference time, we propose to associate detected instances to tracklets based on the max-likelihood transition state under motion-constrained bi-directional walks. Walker is the first self-supervised tracker to achieve competitive performance on MOT17, DanceTrack, and BDD100K. Remarkably, our proposal outperforms the previous self-supervised trackers even when drastically reducing the annotation requirements by up to 400x."