Vision foundation models (VFMs) trained on large-scale image datasets provide high-quality features that have significantly advanced$2 D$visual recognition. However, their potential in 3D scene segmentation remains largely untapped, despite the common availability of$2 D$images alongside 3D point cloud datasets. While significant research has been dedicated to 2D-3D fusion, recent state-of-the-art 3D methods predominantly focus on 3D data, leaving the integration of VFMs into 3D models underexplored. In this work, we challenge this trend by introducing DITR, a generally applicable approach that extracts$2 D$foundation model features, projects them to 3D, and finally injects them into a 3D point cloud segmentation model. DITR achieves state-of-the-art results on both indoor and outdoor 3D semantic segmentation benchmarks. To enable the use of VFMs even when images are unavailable during inference, we additionally propose to pretrain 3D models by distilling 2D foundation models. By initializing the 3D backbone with knowledge distilled from 2D VFMs, we create a strong basis for downstream 3D segmentation tasks, ultimately boosting performance across various datasets.

Vision Transformers (ViTs) have shown remarkable performance and scalability across various computer vision tasks. To apply single-scale ViTs to image segmentation, existing methods adopt a convolutional adapter to generate multi-scale features, a pixel decoder to fuse these features, and a Transformer decoder that uses the fused features to make predictions. In this paper, we show that the inductive biases introduced by these task-specific components can instead be learned by the ViT itself, given sufficiently large models and extensive pre-training. Based on these findings, we introduce the Encoder-Only Mask Transformer (EoMT), which repurposes the plain ViT architecture to conduct image segmentation. With large-scale models and pre-training, EoMT obtains a segmentation accuracy similar to state-of-the-art models that use task-specific components. At the same time, EoMT is significantly faster than these methods due to its architectural simplicity, e.g., up to 4 × faster with ViT-L. Across a range of model sizes, EoMT demonstrates an optimal balance between segmentation accuracy and prediction speed, suggesting that compute resources are better spent on scaling the ViT itself rather than adding architectural complexity. Code: https://www.tue-mps.org/eomt/.

Predicting the motion of other agents in a scene is highly relevant for autonomous driving, as it allows a self-driving car to anticipate. Inspired by the success of decoder-only models for language modeling, we propose DONUT, a Decoder-Only Network for Unrolling Trajectories. Unlike existing encoder-decoder forecasting models, we encode historical trajectories and predict future trajectories with a single autoregressive model. This allows the model to make iterative predictions in a consistent manner, and ensures that the model is always provided with up-to-date information, thereby enhancing performance. Furthermore, inspired by multi-token prediction for language modeling, we introduce an 'overprediction' strategy that gives the model the auxiliary task of predicting trajectories at longer temporal horizons. This allows the model to better anticipate the future and further improves performance. Through experiments, we demonstrate that our decoder-only approach outperforms the encoder-decoder baseline, and achieves new state-of-the-art results on the Argoverse 2 single-agent motion forecasting benchmark.

Recent work showed that large diffusion models can be reused as highly precise monocular depth estimators by casting depth estimation as an image-conditional image generation task. While the proposed model achieved state-of-the-art results, high computational demands due to multi-step inference limited its use in many scenarios. In this paper, we show that the perceived inefficiency was caused by a flaw in the inference pipeline that has so far gone unnoticed. The fixed model performs comparably to the best previously reported configuration while being more than 200x faster. To optimize for downstream task performance, we perform end-to-end fine-tuning on top of the single-step model with task-specific losses and get a deterministic model that outperforms all other diffusion-based depth and normal estimation models on common zero-shot benchmarks. We surprisingly find that this fine-tuning protocol also works directly on Stable Diffusion and achieves comparable performance to current state-of-the-art diffusion-based depth and normal estimation models, calling into question some of the conclusions drawn from prior works.

Part-aware panoptic segmentation (PPS) requires (a) that each foreground object and background region in an image is segmented and classified, and (b) that all parts within foreground objects are segmented, classified and linked to their parent object. Existing methods approach PPS by separately conducting object-level and part-level segmentation. However, their part-level predictions are not linked to individual parent objects. Therefore, their learning objective is not aligned with the PPS task objective, which harms the PPS performance. To solve this, and make more accurate PPS predictions, we propose Task-Aligned Part-aware Panoptic Segmentation (TAPPS). This method uses a set of shared queries to jointly predict (a) object-level segments, and (b) the part-level segments within those same objects. As a result, TAPPS learns to predict part-level segments that are linked to individual parent objects, aligning the learning objective with the task objective, and allowing TAPPS to leverage joint object-part representations. With experiments, we show that TAPPS considerably outperforms methods that predict objects and parts separately, and achieves new state-of-the-art PPS results.

This work presents Adaptive Local-then-Global Merging (ALGM), a token reduction method for semantic segmentation networks that use plain Vision Transformers. ALGM merges tokens in two stages: (1) In the first network layer, it merges similar tokens within a small local window and (2) halfway through the network, it merges similar tokens across the entire image. This is motivated by an analysis in which we found that, in those situations, tokens with a high cosine similarity can likely be merged without a drop in segmentation quality. With extensive experiments across multiple datasets and network configurations, we show that ALGM not only significantly improves the throughput by up to 100%, but can also enhance the mean IoU by up to + 1.1, thereby achieving a better trade-off between segmentation quality and efficiency than existing methods. Moreover, our approach is adaptive during inference, meaning that the same model can be used for optimal efficiency or accuracy, depending on the application. Code is available at https://tue-mps.github.io/ALGM.

Learning anticipation in Multi-Agent Reinforcement Learning (MARL) is a reasoning paradigm where agents anticipate the learning steps of other agents to improve cooperation among themselves. As MARL uses gradient-based optimization, learning anticipation requires using Higher-Order Gradients (HOG), with so-called HOG methods. Existing HOG methods are based on policy parameter anticipation, i.e., agents anticipate the changes in policy parameters of other agents. Currently, however, these existing HOG methods have only been developed for differentiable games or games with small state spaces. In this work, we demonstrate that in the case of non-differentiable games with large state spaces, existing HOG methods do not perform well and are inefficient due to their inherent limitations related to policy parameter anticipation and multiple sampling stages. To overcome these problems, we propose Off-Policy Action Anticipation (OffPA2), a novel framework that approaches learning anticipation through action anticipation, i.e., agents anticipate the changes in actions of other agents, via off-policy sampling. We theoretically analyze our proposed OffPA2 and employ it to develop multiple HOG methods that are applicable to non-differentiable games with large state spaces. We conduct a large set of experiments and illustrate that our proposed HOG methods outperform the existing ones regarding efficiency and performance.

This paper introduces Content-aware Token Sharing (CTS), a token reduction approach that improves the computational efficiency of semantic segmentation networks that use Vision Transformers (ViTs). Existing works have proposed token reduction approaches to improve the efficiency of ViT-based image classification networks, but these methods are not directly applicable to semantic segmentation, which we address in this work. We observe that, for semantic segmentation, multiple image patches can share a token if they contain the same semantic class, as they contain redundant information. Our approach leverages this by employing an efficient, class-agnostic policy network that predicts if image patches contain the same semantic class, and lets them share a token if they do. With experiments, we explore the critical design choices of CTS and show its effectiveness on the ADE20K, Pascal Context and Cityscapes datasets, various ViT backbones, and different segmentation decoders. With Content-aware Token Sharing, we are able to reduce the number of processed tokens by up to 44%, without diminishing the segmentation quality.

Unified panoptic segmentation methods are achieving state-of-the-art results on several datasets. To achieve these results on high-resolution datasets, these methods apply crop-based training. In this work, we find that, although crop-based training is advantageous in general, it also has a harmful side-effect. Specifically, it limits the ability of unified networks to discriminate between large object instances, causing them to make predictions that are confused between multiple instances. To solve this, we propose Intra-Batch Supervision (IBS), which improves a network’s ability to discriminate between instances by introducing additional supervision using multiple images from the same batch. We show that, with our IBS, we successfully address the confusion problem and consistently improve the performance of unified networks. For the high-resolution Cityscapes and Mapillary Vistas datasets, we achieve improvements of up to +2.5 on the Panoptic Quality for thing classes, and even more considerable gains of up to +5.8 on both the pixel accuracy and pixel precision, which we identify as better metrics to capture the confusion problem.

For autonomous vehicles and mobile robots to safely operate in the real world, i.e., the wild, scene understanding models should perform well in the many different scenarios that can be encountered. In reality, these scenarios are not all represented in the model’s training data, leading to poor performance. To tackle this, current training strategies attempt to either exploit additional unlabeled data with unsupervised domain adaptation (UDA), or to reduce overfitting using the limited available labeled data with domain generalization (DG). However, it is not clear from current literature which of these methods allows for better generalization to unseen data from the wild. Therefore, in this work, we present an evaluation framework in which the generalization capabilities of state-of-the-art UDA and DG methods can be compared fairly. From this evaluation, we find that UDA methods, which leverage unlabeled data, outperform DG methods in terms of generalization, and can deliver similar performance on unseen data as fully-supervised training methods that require all data to be labeled. We show that semantic segmentation performance can be increased up to 30% for a priori unknown data without using any extra labeled data.

In this work, we propose a single deep neural network for panoptic segmentation, for which the goal is to provide each individual pixel of an input image with a class label, as in semantic segmentation, as well as a unique identifier for specific objects in an image, following instance segmentation. Our network makes joint semantic and instance segmentation predictions and combines these to form an output in the panoptic format. This has two main benefits: firstly, the entire panoptic prediction is made in one pass, reducing the required computation time and resources; secondly, by learning the tasks jointly, information is shared between the two tasks, thereby improving performance. Our network is evaluated on two street scene datasets: Cityscapes and Mapillary Vistas. By leveraging information exchange and improving the merging heuristics, we increase the performance of the single network, and achieve a score of 23.9 on the Panoptic Quality (PQ) metric on Mapillary Vistas validation, with an input resolution of 640 × 900 pixels. On Cityscapes validation, our method achieves a PQ score of 45.9 with an input resolution of 512 × 1024 pixels. Moreover, our method decreases the prediction time by a factor of 2 with respect to separate networks.