Generalization to new domains not seen during training is one of the long-standing goals and challenges in deploying neural networks in real-world applications. Existing generalization techniques necessitate substantial data augmentation, potentially sourced from external datasets, and aim at learning invariant representations by imposing various alignment constraints. Large-scale pretraining has recently shown promising generalization capabilities, along with the potential of bridging different modalities. For instance, the recent advent of vision-language models like CLIP has opened the doorway for vision models to exploit the textual modality. In this paper, we introduce a simple framework for generalizing semantic segmentation networks by employing language as the source of randomization. Our recipe comprises three key ingredients: i) the preservation of the intrinsic CLIP robustness through minimal fine-tuning, ii) language-driven local style augmentation, and iii) randomization by locally mixing the source and augmented styles during training. Extensive experiments report state-of-the-art results on various generalization benchmarks. The code will be made available.
Self-supervised image networks can be used to address complex 2D tasks (e.g., semantic segmentation, object discovery) very efficiently and with little or no downstream supervision. However, self-supervised 3D networks on lidar data do not perform as well for now. A few methods therefore propose to distill high-quality self-supervised 2D features into 3D networks. The most recent ones doing so on autonomous driving data show promising results. Yet, a performance gap persists between these distilled features and fully-supervised ones. In this work, we revisit 2D-to-3D distillation. First, we propose, for semantic segmentation, a simple approach that leads to a significant improvement compared to prior 3D distillation methods. Second, we show that distillation in high capacity 3D networks is key to reach high quality 3D features. This actually allows us to significantly close the gap between unsupervised distilled 3D features and fully-supervised ones. Last, we show that our high-quality distilled representations can also be used for open-vocabulary segmentation and background/foreground discovery.
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segmentation in urban environments, with a particular focus on natural adversarial scenarios. The report presents the results of 19 submitted entries, with numerous techniques drawing inspiration from cutting-edge uncertainty quantification methodologies presented at prominent conferences in the fields of computer vision and machine learning and journals over the past few years. Within this document, the challenge is introduced, shedding light on its purpose and objectives, which primarily revolved around enhancing the robustness of semantic segmentation in urban scenes under varying natural adversarial conditions. The report then delves into the top-performing solutions. Moreover, the document aims to provide a comprehensive overview of the diverse solutions deployed by all participants. By doing so, it seeks to offer readers a deeper insight into the array of strategies that can be leveraged to effectively handle the inherent uncertainties associated with autonomous driving and semantic segmentation, especially within urban environments.
This paper examines the robustness of a multi-modal computer vision model, CLIP (Contrastive Language-Image Pretraining), in the context of unsupervised learning. The main objective is twofold: first, to evaluate the robustness of CLIP, and second, to explore strategies for augmenting its robustness. To achieve this, we introduce a novel approach named LP-CLIP. This technique involves the distillation of CLIP features through the incorporation of a linear probing layer positioned atop its encoding structure. This newly added layer is trained utilizing pseudo-labels produced by CLIP, coupled with a self-training strategy. The LP-CLIP technique offers a promising approach to enhance the robustness of CLIP without the need for annotations. By leveraging a simple linear probing layer, we aim to improve the model's ability to withstand various uncertainties and challenges commonly encountered in real-world scenarios. Importantly, our approach does not rely on annotated data, which makes it particularly valuable in situations where labeled data might be scarce or costly to obtain. Our proposed approach increases the robustness of CLIP with SOTA results compared to supervised technique on various datasets.
Semantic segmentation techniques have shown significant progress in recent years, but their robustness to real-world perturbations and data samples not seen during training remains a challenge, particularly in safety-critical applications. In this paper, we propose a novel approach to improve the robustness of semantic segmentation techniques by leveraging the synergy between label-to-image generators and image-to-label segmentation models. Specifically, we design and train Robusta, a novel robust conditional generative adversarial network to generate realistic and plausible perturbed or outlier images that can be used to train reliable segmentation models. We conduct in-depth studies of the proposed generative model, assess the performance and robustness of the downstream segmentation network, and demonstrate that our approach can significantly enhance the robustness of semantic segmentation techniques in the face of real-world perturbations, distribution shifts, and out-of-distribution samples. Our results suggest that this approach could be valuable in safety-critical applications, where the reliability of semantic segmentation techniques is of utmost importance and comes with a limited computational budget in inference. We will release our code shortly.
Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks for very large fully-annotated datasets. Different classes of self-supervised learning offer representations with either good contextual reasoning properties, e.g., using masked image modeling strategies, or invariance to image perturbations, e.g., with contrastive methods. In this work, we propose a single-stage and standalone method, MOCA, which unifies both desired properties using novel mask-and-predict objectives defined with high-level features (instead of pixel-level details). Moreover, we show how to effectively employ both learning paradigms in a synergistic and computation-efficient way. Doing so, we achieve new state-of-the-art results on low-shot settings and strong experimental results in various evaluation protocols with a training that is at least 3 times faster than prior methods.
Casting semantic segmentation of outdoor LiDAR point clouds as a 2D problem, e.g., via range projection, is an effective and popular approach. These projection-based methods usually benefit from fast computations and, when combined with techniques which use other point cloud representations, achieve state-of-the-art results. Today, projection-based methods leverage 2D CNNs but recent advances in computer vision show that vision transformers (ViTs) have achieved state-of-the-art results in many image-based benchmarks. In this work, we question if projection-based methods for 3D semantic segmentation can benefit from these latest improvements on ViTs. We answer positively but only after combining them with three key ingredients: (a) ViTs are notoriously hard to train and require a lot of training data to learn powerful representations. By preserving the same backbone architecture as for RGB images, we can exploit the knowledge from long training on large image collections that are much cheaper to acquire and annotate than point clouds. We reach our best results with pre-trained ViTs on large image datasets. (b) We compensate ViTs' lack of inductive bias by substituting a tailored convolutional stem for the classical linear embedding layer. (c) We refine pixel-wise predictions with a convolutional decoder and a skip connection from the convolutional stem to combine low-level but fine-grained features of the the convolutional stem with the high-level but coarse predictions of the ViT encoder. With these ingredients, we show that our method, called RangeViT, outperforms existing projection-based methods on nuScenes and SemanticKITTI. We provide the implementation code at https://github.com/valeoai/rangevit.
Domain adaptation has been vastly investigated in computer vision but still requires access to target images at train time, which might be intractable in some conditions, especially for long-tail samples. In this paper, we propose the task of `Prompt-driven Zero-shot Domain Adaptation', where we adapt a model trained on a source domain using only a general textual description of the target domain, i.e., a prompt. First, we leverage a pretrained contrastive vision-language model (CLIP) to optimize affine transformations of source features, bringing them closer to target text embeddings, while preserving their content and semantics. Second, we show that augmented features can be used to perform zero-shot domain adaptation for semantic segmentation. Experiments demonstrate that our method significantly outperforms CLIP-based style transfer baselines on several datasets for the downstream task at hand. Our prompt-driven approach even outperforms one-shot unsupervised domain adaptation on some datasets, and gives comparable results on others. The code is available at https://github.com/astra-vision/PODA.
Deep Ensembles (DE) are a prominent approach achieving excellent performance on key metrics such as accuracy, calibration, uncertainty estimation, and out-of-distribution detection. However, hardware limitations of real-world systems constrain to smaller ensembles and lower capacity networks, significantly deteriorating their performance and properties. We introduce Packed-Ensembles (PE), a strategy to design and train lightweight structured ensembles by carefully modulating the dimension of their encoding space. We leverage grouped convolutions to parallelize the ensemble into a single common backbone and forward pass to improve training and inference speeds. PE is designed to work under the memory budget of a single standard neural network. Through extensive studies we show that PE faithfully preserve the properties of DE, e.g., diversity, and match their performance in terms of accuracy, calibration, out-of-distribution detection and robustness to distribution shift.