Open-vocabulary object detection (OVOD) has recently gained significant attention as a crucial step toward achieving human-like visual intelligence. Existing OVOD methods extend target vocabulary from pre-defined categories to open-world by transferring knowledge of arbitrary concepts from vision-language pre-training models to the detectors. While previous methods have shown remarkable successes, they suffer from indirect supervision or limited transferable concepts. In this paper, we propose a simple yet effective method to directly learn region-text alignment for arbitrary concepts. Specifically, the proposed method aims to learn arbitrary image-to-text mapping for pseudo-labeling of arbitrary concepts, named Pseudo-Labeling for Arbitrary Concepts (PLAC). The proposed method shows competitive performance on the standard OVOD benchmark for noun concepts and a large improvement on referring expression comprehension benchmark for arbitrary concepts.
In-context learning allows adapting a model to new tasks given a task description at test time. In this paper, we present IMProv - a generative model that is able to in-context learn visual tasks from multimodal prompts. Given a textual description of a visual task (e.g. "Left: input image, Right: foreground segmentation"), a few input-output visual examples, or both, the model in-context learns to solve it for a new test input. We train a masked generative transformer on a new dataset of figures from computer vision papers and their associated captions, together with a captioned large-scale image-text dataset. During inference time, we prompt the model with text and/or image task example(s) and have the model inpaint the corresponding output. We show that training our model with text conditioning and scaling the dataset size improves in-context learning for computer vision tasks by over +10\% AP for Foreground Segmentation, over +5\% gains in AP for Single Object Detection, and almost 20\% lower LPIPS in Colorization. Our empirical results suggest that vision and language prompts are complementary and it is advantageous to use both to achieve better in-context learning performance. Project page is available at https://jerryxu.net/IMProv .
Recently, the rise of query-based Transformer decoders is reshaping camera-based 3D object detection. These query-based decoders are surpassing the traditional dense BEV (Bird's Eye View)-based methods. However, we argue that dense BEV frameworks remain important due to their outstanding abilities in depth estimation and object localization, depicting 3D scenes accurately and comprehensively. This paper aims to address the drawbacks of the existing dense BEV-based 3D object detectors by introducing our proposed enhanced components, including a CRF-modulated depth estimation module enforcing object-level consistencies, a long-term temporal aggregation module with extended receptive fields, and a two-stage object decoder combining perspective techniques with CRF-modulated depth embedding. These enhancements lead to a "modernized" dense BEV framework dubbed BEVNeXt. On the nuScenes benchmark, BEVNeXt outperforms both BEV-based and query-based frameworks under various settings, achieving a state-of-the-art result of 64.2 NDS on the nuScenes test set. Code will be available at \url{https://github.com/woxihuanjiangguo/BEVNeXt}.
Domain generalization (DG) remains a significant challenge for perception based on deep neural networks (DNNs), where domain shifts occur due to synthetic data, lighting, weather, or location changes. Vision-language models (VLMs) marked a large step for the generalization capabilities and have been already applied to various tasks. Very recently, first approaches utilized VLMs for domain generalized segmentation and object detection and obtained strong generalization. However, all these approaches rely on complex modules, feature augmentation frameworks or additional models. Surprisingly and in contrast to that, we found that simple fine-tuning of vision-language pre-trained models yields competitive or even stronger generalization results while being extremely simple to apply. Moreover, we found that vision-language pre-training consistently provides better generalization than the previous standard of vision-only pre-training. This challenges the standard of using ImageNet-based transfer learning for domain generalization. Fully fine-tuning a vision-language pre-trained model is capable of reaching the domain generalization SOTA when training on the synthetic GTA5 dataset. Moreover, we confirm this observation for object detection on a novel synthetic-to-real benchmark. We further obtain superior generalization capabilities by reaching 77.9% mIoU on the popular Cityscapes-to-ACDC benchmark. We also found improved in-domain generalization, leading to an improved SOTA of 86.4% mIoU on the Cityscapes test set marking the first place on the leaderboard.
Human-centric perception tasks, e.g., pedestrian detection, skeleton-based action recognition, and pose estimation, have wide industrial applications, such as metaverse and sports analysis. There is a recent surge to develop human-centric foundation models that can benefit a broad range of human-centric perception tasks. While many human-centric foundation models have achieved success, they did not explore 3D and vision-language tasks for human-centric and required task-specific finetuning. These limitations restrict their application to more downstream tasks and situations. To tackle these problems, we present Hulk, the first multimodal human-centric generalist model, capable of addressing 2D vision, 3D vision, skeleton-based, and vision-language tasks without task-specific finetuning. The key to achieving this is condensing various task-specific heads into two general heads, one for discrete representations, e.g., languages, and the other for continuous representations, e.g., location coordinates. The outputs of two heads can be further stacked into four distinct input and output modalities. This uniform representation enables Hulk to treat diverse human-centric tasks as modality translation, integrating knowledge across a wide range of tasks. Comprehensive evaluations of Hulk on 12 benchmarks covering 8 human-centric tasks demonstrate the superiority of our proposed method, achieving state-of-the-art performance in 11 benchmarks. The code is available on https://github.com/OpenGVLab/Hulk.
Our study assesses the adversarial robustness of LiDAR-camera fusion models in 3D object detection. We introduce an attack technique that, by simply adding a limited number of physically constrained adversarial points above a car, can make the car undetectable by the fusion model. Experimental results reveal that even without changes to the image data channel, the fusion model can be deceived solely by manipulating the LiDAR data channel. This finding raises safety concerns in the field of autonomous driving. Further, we explore how the quantity of adversarial points, the distance between the front-near car and the LiDAR-equipped car, and various angular factors affect the attack success rate. We believe our research can contribute to the understanding of multi-sensor robustness, offering insights and guidance to enhance the safety of autonomous driving.
The representation gap between teacher and student is an emerging topic in knowledge distillation (KD). To reduce the gap and improve the performance, current methods often resort to complicated training schemes, loss functions, and feature alignments, which are task-specific and feature-specific. In this paper, we state that the essence of these methods is to discard the noisy information and distill the valuable information in the feature, and propose a novel KD method dubbed DiffKD, to explicitly denoise and match features using diffusion models. Our approach is based on the observation that student features typically contain more noises than teacher features due to the smaller capacity of student model. To address this, we propose to denoise student features using a diffusion model trained by teacher features. This allows us to perform better distillation between the refined clean feature and teacher feature. Additionally, we introduce a light-weight diffusion model with a linear autoencoder to reduce the computation cost and an adaptive noise matching module to improve the denoising performance. Extensive experiments demonstrate that DiffKD is effective across various types of features and achieves state-of-the-art performance consistently on image classification, object detection, and semantic segmentation tasks. Code is available at https://github.com/hunto/DiffKD.
Current research is primarily dedicated to advancing the accuracy of camera-only 3D object detectors (apprentice) through the knowledge transferred from LiDAR- or multi-modal-based counterparts (expert). However, the presence of the domain gap between LiDAR and camera features, coupled with the inherent incompatibility in temporal fusion, significantly hinders the effectiveness of distillation-based enhancements for apprentices. Motivated by the success of uni-modal distillation, an apprentice-friendly expert model would predominantly rely on camera features, while still achieving comparable performance to multi-modal models. To this end, we introduce VCD, a framework to improve the camera-only apprentice model, including an apprentice-friendly multi-modal expert and temporal-fusion-friendly distillation supervision. The multi-modal expert VCD-E adopts an identical structure as that of the camera-only apprentice in order to alleviate the feature disparity, and leverages LiDAR input as a depth prior to reconstruct the 3D scene, achieving the performance on par with other heterogeneous multi-modal experts. Additionally, a fine-grained trajectory-based distillation module is introduced with the purpose of individually rectifying the motion misalignment for each object in the scene. With those improvements, our camera-only apprentice VCD-A sets new state-of-the-art on nuScenes with a score of 63.1% NDS.
Vision Transformers have achieved impressive performance in many vision tasks. While the token mixer or attention block has been studied in great detail, much less research has been devoted to the channel mixer or feature mixing block (FFN or MLP), which accounts for a significant portion of of the model parameters and computation. In this work, we show that the dense MLP connections can be replaced with a block diagonal MLP structure that supports larger expansion ratios by splitting MLP features into groups. To improve the feature clusters formed by this structure we propose the use of a lightweight, parameter-free, channel covariance attention (CCA) mechanism as a parallel branch during training. This enables gradual feature mixing across channel groups during training whose contribution decays to zero as the training progresses to convergence. In result, the CCA block can be discarded during inference, enabling enhanced performance at no additional computational cost. The resulting $\textit{Scalable CHannEl MixEr}$ (SCHEME) can be plugged into any ViT architecture to obtain a gamut of models with different trade-offs between complexity and performance by controlling the block diagonal MLP structure. This is shown by the introduction of a new family of SCHEMEformer models. Experiments on image classification, object detection, and semantic segmentation, with different ViT backbones, consistently demonstrate substantial accuracy gains over existing designs, especially for lower complexity regimes. The SCHEMEformer family is shown to establish new Pareto frontiers for accuracy vs FLOPS, accuracy vs model size, and accuracy vs throughput, especially for fast transformers of small size.
Multimodal (e.g., RGB-Depth/RGB-Thermal) fusion has shown great potential for improving semantic segmentation in complex scenes (e.g., indoor/low-light conditions). Existing approaches often fully fine-tune a dual-branch encoder-decoder framework with a complicated feature fusion strategy for achieving multimodal semantic segmentation, which is training-costly due to the massive parameter updates in feature extraction and fusion. To address this issue, we propose a surprisingly simple yet effective dual-prompt learning network (dubbed DPLNet) for training-efficient multimodal (e.g., RGB-D/T) semantic segmentation. The core of DPLNet is to directly adapt a frozen pre-trained RGB model to multimodal semantic segmentation, reducing parameter updates. For this purpose, we present two prompt learning modules, comprising multimodal prompt generator (MPG) and multimodal feature adapter (MFA). MPG works to fuse the features from different modalities in a compact manner and is inserted from shadow to deep stages to generate the multi-level multimodal prompts that are injected into the frozen backbone, while MPG adapts prompted multimodal features in the frozen backbone for better multimodal semantic segmentation. Since both the MPG and MFA are lightweight, only a few trainable parameters (3.88M, 4.4% of the pre-trained backbone parameters) are introduced for multimodal feature fusion and learning. Using a simple decoder (3.27M parameters), DPLNet achieves new state-of-the-art performance or is on a par with other complex approaches on four RGB-D/T semantic segmentation datasets while satisfying parameter efficiency. Moreover, we show that DPLNet is general and applicable to other multimodal tasks such as salient object detection and video semantic segmentation. Without special design, DPLNet outperforms many complicated models. Our code will be available at github.com/ShaohuaDong2021/DPLNet.
Creating radio galaxy catalogues from next-generation deep surveys requires automated identification of associated components of extended sources and their corresponding infrared hosts. In this paper, we introduce RadioGalaxyNET, a multimodal dataset, and a suite of novel computer vision algorithms designed to automate the detection and localization of multi-component extended radio galaxies and their corresponding infrared hosts. The dataset comprises 4,155 instances of galaxies in 2,800 images with both radio and infrared channels. Each instance provides information about the extended radio galaxy class, its corresponding bounding box encompassing all components, the pixel-level segmentation mask, and the keypoint position of its corresponding infrared host galaxy. RadioGalaxyNET is the first dataset to include images from the highly sensitive Australian Square Kilometre Array Pathfinder (ASKAP) radio telescope, corresponding infrared images, and instance-level annotations for galaxy detection. We benchmark several object detection algorithms on the dataset and propose a novel multimodal approach to simultaneously detect radio galaxies and the positions of infrared hosts.
Adversarial patches exemplify the tangible manifestation of the threat posed by adversarial attacks on Machine Learning (ML) models in real-world scenarios. Robustness against these attacks is of the utmost importance when designing computer vision applications, especially for safety-critical domains such as CCTV systems. In most practical situations, monitoring open spaces requires multi-view systems to overcome acquisition challenges such as occlusion handling. Multiview object systems are able to combine data from multiple views, and reach reliable detection results even in difficult environments. Despite its importance in real-world vision applications, the vulnerability of multiview systems to adversarial patches is not sufficiently investigated. In this paper, we raise the following question: Does the increased performance and information sharing across views offer as a by-product robustness to adversarial patches? We first conduct a preliminary analysis showing promising robustness against off-the-shelf adversarial patches, even in an extreme setting where we consider patches applied to all views by all persons in Wildtrack benchmark. However, we challenged this observation by proposing two new attacks: (i) In the first attack, targeting a multiview CNN, we maximize the global loss by proposing gradient projection to the different views and aggregating the obtained local gradients. (ii) In the second attack, we focus on a Transformer-based multiview framework. In addition to the focal loss, we also maximize the transformer-specific loss by dissipating its attention blocks. Our results show a large degradation in the detection performance of victim multiview systems with our first patch attack reaching an attack success rate of 73% , while our second proposed attack reduced the performance of its target detector by 62%
Despite remarkable achievements in video synthesis, achieving granular control over complex dynamics, such as nuanced movement among multiple interacting objects, still presents a significant hurdle for dynamic world modeling, compounded by the necessity to manage appearance and disappearance, drastic scale changes, and ensure consistency for instances across frames. These challenges hinder the development of video generation that can faithfully mimic real-world complexity, limiting utility for applications requiring high-level realism and controllability, including advanced scene simulation and training of perception systems. To address that, we propose TrackDiffusion, a novel video generation framework affording fine-grained trajectory-conditioned motion control via diffusion models, which facilitates the precise manipulation of the object trajectories and interactions, overcoming the prevalent limitation of scale and continuity disruptions. A pivotal component of TrackDiffusion is the instance enhancer, which explicitly ensures inter-frame consistency of multiple objects, a critical factor overlooked in the current literature. Moreover, we demonstrate that generated video sequences by our TrackDiffusion can be used as training data for visual perception models. To the best of our knowledge, this is the first work to apply video diffusion models with tracklet conditions and demonstrate that generated frames can be beneficial for improving the performance of object trackers.
3D object detection in Bird's-Eye-View (BEV) space has recently emerged as a prevalent approach in the field of autonomous driving. Despite the demonstrated improvements in accuracy and velocity estimation compared to perspective view methods, the deployment of BEV-based techniques in real-world autonomous vehicles remains challenging. This is primarily due to their reliance on vision-transformer (ViT) based architectures, which introduce quadratic complexity with respect to the input resolution. To address this issue, we propose an efficient BEV-based 3D detection framework called BEVENet, which leverages a convolutional-only architectural design to circumvent the limitations of ViT models while maintaining the effectiveness of BEV-based methods. Our experiments show that BEVENet is 3$\times$ faster than contemporary state-of-the-art (SOTA) approaches on the NuScenes challenge, achieving a mean average precision (mAP) of 0.456 and a nuScenes detection score (NDS) of 0.555 on the NuScenes validation dataset, with an inference speed of 47.6 frames per second. To the best of our knowledge, this study stands as the first to achieve such significant efficiency improvements for BEV-based methods, highlighting their enhanced feasibility for real-world autonomous driving applications.
Obtaining large pre-trained models that can be fine-tuned to new tasks with limited annotated samples has remained an open challenge for medical imaging data. While pre-trained deep networks on ImageNet and vision-language foundation models trained on web-scale data are prevailing approaches, their effectiveness on medical tasks is limited due to the significant domain shift between natural and medical images. To bridge this gap, we introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets. We have collected approximately 1.3 million medical images from 55 publicly available datasets, covering a large number of organs and modalities such as CT, MRI, X-ray, and Ultrasound. We benchmark several state-of-the-art self-supervised algorithms on this dataset and propose a novel self-supervised contrastive learning algorithm using a graph-matching formulation. The proposed approach makes three contributions: (i) it integrates prior pair-wise image similarity metrics based on local and global information; (ii) it captures the structural constraints of feature embeddings through a loss function constructed via a combinatorial graph-matching objective; and (iii) it can be trained efficiently end-to-end using modern gradient-estimation techniques for black-box solvers. We thoroughly evaluate the proposed LVM-Med on 15 downstream medical tasks ranging from segmentation and classification to object detection, and both for the in and out-of-distribution settings. LVM-Med empirically outperforms a number of state-of-the-art supervised, self-supervised, and foundation models. For challenging tasks such as Brain Tumor Classification or Diabetic Retinopathy Grading, LVM-Med improves previous vision-language models trained on 1 billion masks by 6-7% while using only a ResNet-50.
End-to-end autonomous driving is a fully differentiable machine learning system that takes raw sensor input data and other metadata as prior information and directly outputs the ego vehicle's control signals or planned trajectories. This paper attempts to systematically review all recent Machine Learning-based techniques to perform this end-to-end task, including, but not limited to, object detection, semantic scene understanding, object tracking, trajectory predictions, trajectory planning, vehicle control, social behavior, and communications. This paper focuses on recent fully differentiable end-to-end reinforcement learning and deep learning-based techniques. Our paper also builds taxonomies of the significant approaches by sub-grouping them and showcasing their research trends. Finally, this survey highlights the open challenges and points out possible future directions to enlighten further research on the topic.
Construction of a universal detector poses a crucial question: How can we most effectively train a model on a large mixture of datasets? The answer lies in learning dataset-specific features and ensembling their knowledge but do all this in a single model. Previous methods achieve this by having separate detection heads on a common backbone but that results in a significant increase in parameters. In this work, we present Mixture-of-Experts as a solution, highlighting that MoEs are much more than a scalability tool. We propose Dataset-Aware Mixture-of-Experts, DAMEX where we train the experts to become an `expert' of a dataset by learning to route each dataset tokens to its mapped expert. Experiments on Universal Object-Detection Benchmark show that we outperform the existing state-of-the-art by average +10.2 AP score and improve over our non-MoE baseline by average +2.0 AP score. We also observe consistent gains while mixing datasets with (1) limited availability, (2) disparate domains and (3) divergent label sets. Further, we qualitatively show that DAMEX is robust against expert representation collapse.
Vision transformers (ViTs) have emerged as a prevalent architecture for vision tasks owing to their impressive performance. However, when it comes to handling long token sequences, especially in dense prediction tasks that require high-resolution input, the complexity of ViTs increases significantly. Notably, dense prediction tasks, such as semantic segmentation or object detection, emphasize more on the contours or shapes of objects, while the texture inside objects is less informative. Motivated by this observation, we propose to apply adaptive resolution for different regions in the image according to their importance. Specifically, at the intermediate layer of the ViT, we utilize a spatial-aware density-based clustering algorithm to select representative tokens from the token sequence. Once the representative tokens are determined, we proceed to merge other tokens into their closest representative token. Consequently, semantic similar tokens are merged together to form low-resolution regions, while semantic irrelevant tokens are preserved independently as high-resolution regions. This strategy effectively reduces the number of tokens, allowing subsequent layers to handle a reduced token sequence and achieve acceleration. We evaluate our proposed method on three different datasets and observe promising performance. For example, the "Segmenter ViT-L" model can be accelerated by 48% FPS without fine-tuning, while maintaining the performance. Additionally, our method can be applied to accelerate fine-tuning as well. Experimental results demonstrate that we can save 52% training time while accelerating 2.46 times FPS with only a 0.09% performance drop. The code is available at https://github.com/caddyless/ailurus/tree/main.
Neural network based computer vision systems are typically built on a backbone, a pretrained or randomly initialized feature extractor. Several years ago, the default option was an ImageNet-trained convolutional neural network. However, the recent past has seen the emergence of countless backbones pretrained using various algorithms and datasets. While this abundance of choice has led to performance increases for a range of systems, it is difficult for practitioners to make informed decisions about which backbone to choose. Battle of the Backbones (BoB) makes this choice easier by benchmarking a diverse suite of pretrained models, including vision-language models, those trained via self-supervised learning, and the Stable Diffusion backbone, across a diverse set of computer vision tasks ranging from classification to object detection to OOD generalization and more. Furthermore, BoB sheds light on promising directions for the research community to advance computer vision by illuminating strengths and weakness of existing approaches through a comprehensive analysis conducted on more than 1500 training runs. While vision transformers (ViTs) and self-supervised learning (SSL) are increasingly popular, we find that convolutional neural networks pretrained in a supervised fashion on large training sets still perform best on most tasks among the models we consider. Moreover, in apples-to-apples comparisons on the same architectures and similarly sized pretraining datasets, we find that SSL backbones are highly competitive, indicating that future works should perform SSL pretraining with advanced architectures and larger pretraining datasets. We release the raw results of our experiments along with code that allows researchers to put their own backbones through the gauntlet here: https://github.com/hsouri/Battle-of-the-Backbones
Deriving reliable region-word alignment from image-text pairs is critical to learn object-level vision-language representations for open-vocabulary object detection. Existing methods typically rely on pre-trained or self-trained vision-language models for alignment, which are prone to limitations in localization accuracy or generalization capabilities. In this paper, we propose CoDet, a novel approach that overcomes the reliance on pre-aligned vision-language space by reformulating region-word alignment as a co-occurring object discovery problem. Intuitively, by grouping images that mention a shared concept in their captions, objects corresponding to the shared concept shall exhibit high co-occurrence among the group. CoDet then leverages visual similarities to discover the co-occurring objects and align them with the shared concept. Extensive experiments demonstrate that CoDet has superior performances and compelling scalability in open-vocabulary detection, e.g., by scaling up the visual backbone, CoDet achieves 37.0 $\text{AP}^m_{novel}$ and 44.7 $\text{AP}^m_{all}$ on OV-LVIS, surpassing the previous SoTA by 4.2 $\text{AP}^m_{novel}$ and 9.8 $\text{AP}^m_{all}$. Code is available at https://github.com/CVMI-Lab/CoDet.