CVPR 2024 论文列表

Existing Knowledge Distillation (KD) methods typically focus on transferring knowledge from a large-capacity teacher to a low-capacity student model achieving substantial success in unimodal knowledge transfer. However existing methods can hardly be extended to Cross-Modal Knowledge Distillation (CMKD) where the knowledge is transferred from a teacher modality to a different student modality with inference only on the distilled student modality. We empirically reveal that the modality gap i.e. modality imbalance and soft label misalignment incurs the ineffectiveness of traditional KD in CMKD. As a solution we propose a novel \underline C ustomized \underline C rossmodal \underline K nowledge \underline D istillation (C^2KD). Specifically to alleviate the modality gap the pre-trained teacher performs bidirectional distillation with the student to provide customized knowledge. The On-the-Fly Selection Distillation(OFSD) strategy is applied to selectively filter out the samples with misaligned soft labels where we distill cross-modal knowledge from non-target classes to avoid the modality imbalance issue. To further provide receptive cross-modal knowledge proxy student and teacher inheriting unimodal and cross-modal knowledge is formulated to progressively transfer cross-modal knowledge through bidirectional distillation. Experimental results on audio-visual image-text and RGB-depth datasets demonstrate that our method can effectively transfer knowledge across modalities achieving superior performance against traditional KD by a large margin.

Neural Architecture Search is a costly practice. The fact that a search space can span a vast number of design choices with each architecture evaluation taking nontrivial overhead makes it hard for an algorithm to sufficiently explore candidate networks. In this paper we propose AutoBuild a scheme which learns to align the latent embeddings of operations and architecture modules with the ground-truth performance of the architectures they appear in. By doing so AutoBuild is capable of assigning interpretable importance scores to architecture modules such as individual operation features and larger macro operation sequences such that high-performance neural networks can be constructed without any need for search. Through experiments performed on state-of-the-art image classification segmentation and Stable Diffusion models we show that by mining a relatively small set of evaluated architectures AutoBuild can learn to build high-quality architectures directly or help to reduce search space to focus on relevant areas finding better architectures that outperform both the original labeled ones and ones found by search baselines. Code available at https://github.com/Ascend-Research/AutoBuild

Radiologists highly desire fully automated versatile AI for medical imaging interpretation. However the lack of extensively annotated large-scale multi-disease datasets has hindered the achievement of this goal. In this paper we explore the feasibility of leveraging language as a naturally high-quality supervision for chest CT imaging. In light of the limited availability of image-report pairs we bootstrap the understanding of 3D chest CT images by distilling chest-related diagnostic knowledge from an extensively pre-trained 2D X-ray expert model. Specifically we propose a language-guided retrieval method to match each 3D CT image with its semantically closest 2D X-ray image and perform pair-wise and semantic relation knowledge distillation. Subsequently we use contrastive learning to align images and reports within the same patient while distinguishing them from the other patients. However the challenge arises when patients have similar semantic diagnoses such as healthy patients potentially confusing if treated as negatives. We introduce a robust contrastive learning that identifies and corrects these false negatives. We train our model with over 12K pairs of chest CT images and radiology reports. Extensive experiments across multiple scenarios including zero-shot learning report generation and fine-tuning processes demonstrate the model's feasibility in interpreting chest CT images.

Inferring scene geometry from images via Structure from Motion is a long-standing and fundamental problem in computer vision. While classical approaches and more recently depth map predictions only focus on the visible parts of a scene the task of scene completion aims to reason about geometry even in occluded regions. With the popularity of NeRF implicit representations also became popular for scene completion by predicting so-called density fields. Unlike explicit approaches e.g. voxel-based methods density fields also allow for accurate depth prediction and novel-view synthesis via image-based rendering. In this work we propose to fuse the scene reconstruction from multiple images and distill this knowledge into a more accurate single-view scene reconstruction. To this end we propose MVBTS to fuse density fields from multiple posed images trained fully self-supervised only from image data. Using knowledge distillation we use MVBTS to train a single-view scene completion network via direct supervision called KDBTS. It achieves state-of-the-art performance on occupancy prediction especially in occluded regions.

Knowledge of lane topology is a core problem in autonomous driving. Aerial imagery can provide high resolution quickly updatable lane source data but detecting lanes from such data has so far been an expensive manual process or where automated solutions exist undrivable and requiring of downstream processing. We propose a method for large-scale lane topology extraction from aerial imagery while ensuring that the resulting lanes are realistic and drivable by introducing a novel Bezier Graph shared parameterisation of Bezier curves. We develop a transformer-based model to predict these Bezier Graphs from input aerial images demonstrating competitive results on the UrbanLaneGraph dataset. We demonstrate that our method generates realistic lane graphs which require both minimal input and minimal downstream processing. We make our code publicly available at https://github.com/driskai/BGFormer

Heterogeneous Federated Learning (HtFL) enables collaborative learning on multiple clients with different model architectures while preserving privacy. Despite recent research progress knowledge sharing in HtFL is still difficult due to data and model heterogeneity. To tackle this issue we leverage the knowledge stored in pre-trained generators and propose a new upload-efficient knowledge transfer scheme called Federated Knowledge-Transfer Loop (FedKTL). Our FedKTL can produce client-task-related prototypical image-vector pairs via the generator's inference on the server. With these pairs each client can transfer pre-existing knowledge from the generator to its local model through an additional supervised local task. We conduct extensive experiments on four datasets under two types of data heterogeneity with 14 kinds of models including CNNs and ViTs. Results show that our upload-efficient FedKTL surpasses seven state-of-the-art methods by up to 7.31% in accuracy. Moreover our knowledge transfer scheme is applicable in scenarios with only one edge client. Code: https://github.com/TsingZ0/FedKTL

Black-Box Knowledge Distillation (B2KD) is a formulated problem for cloud-to-edge model compression with invisible data and models hosted on the server. B2KD faces challenges such as limited Internet exchange and edge-cloud disparity of data distributions. In this paper we formalize a two-step workflow consisting of deprivatization and distillation and theoretically provide a new optimization direction from logits to cell boundary different from direct logits alignment. With its guidance we propose a new method Mapping-Emulation KD (MEKD) that distills a black-box cumbersome model into a lightweight one. Our method does not differentiate between treating soft or hard responses and consists of: 1) deprivatization: emulating the inverse mapping of the teacher function with a generator and 2) distillation: aligning low-dimensional logits of the teacher and student models by reducing the distance of high-dimensional image points. For different teacher-student pairs our method yields inspiring distillation performance on various benchmarks and outperforms the previous state-of-the-art approaches.

Accurately detecting active objects undergoing state changes is essential for comprehending human interactions and facilitating decision-making. The existing methods for active object detection (AOD) primarily rely on visual appearance of the objects within input such as changes in size shape and relationship with hands. However these visual changes can be subtle posing challenges particularly in scenarios with multiple distracting no-change instances of the same category. We observe that the state changes are often the result of an interaction being performed upon the object thus propose to use informed priors about object related plausible interactions (including semantics and visual appearance) to provide more reliable cues for AOD. Specifically we propose a knowledge aggregation procedure to integrate the aforementioned informed priors into oracle queries within the teacher decoder offering more object affordance commonsense to locate the active object. To streamline the inference process and reduce extra knowledge inputs we propose a knowledge distillation approach that encourages the student decoder to mimic the detection capabilities of the teacher decoder using the oracle query by replicating its predictions and attention. Our proposed framework achieves state-of-the-art performance on four datasets namely Ego4D Epic-Kitchens MECCANO and 100DOH which demonstrates the effectiveness of our approach in improving AOD. The code and models are available at https://github.com/idejie/KAD.git.

We present Egocentric Action Scene Graphs (EASGs) a new representation for long-form understanding of egocentric videos. EASGs extend standard manually-annotated representations of egocentric videos such as verb-noun action labels by providing a temporally evolving graph-based description of the actions performed by the camera wearer including interacted objects their relationships and how actions unfold in time. Through a novel annotation procedure we extend the Ego4D dataset adding manually labeled Egocentric Action Scene Graphs which offer a rich set of annotations for long-from egocentric video understanding. We hence define the EASG generation task and provide a baseline approach establishing preliminary benchmarks. Experiments on two downstream tasks action anticipation and activity summarization highlight the effectiveness of EASGs for long-form egocentric video understanding. We will release the dataset and code to replicate experiments and annotations.