Juergen Beyerer

Zeyun Zhong, Manuel Martin, Chengzhi Wu et al.

Recent Large Multimodal Models (LMMs), primarily designed for offline settings, are ill-suited for the dynamic requirements of streaming video. While recent online adaptations improve real-time processing, they still face critical scalability challenges, with resource demands typically growing at least linearly with video duration. To overcome this bottleneck, we propose FlowNar, a novel framework for scalable streaming video narration. The core of FlowNar is a dynamic context management strategy for historical visual context removal, combined with our CLAM (Cross Linear Attentive Memory) module for streaming visual history retention, ensuring bounded visual memory usage and computational complexity, crucial for efficient streaming. We also introduce a realistic self-conditioned evaluation protocol and complementary evaluation metrics to assess streaming narration models under deployment-like conditions. Experiments on the Ego4D, EgoExo4D, and EpicKitchens100 datasets demonstrate that FlowNar substantially improves narration quality over strong baselines while being highly efficient, supporting processing of 10$\times$ longer videos and achieving 3$\times$ higher throughput (FPS). The code is available at https://github.com/zeyun-zhong/FlowNar.

Karim Guirguis, Johannes Meier, George Eskandar et al.

Privacy and memory are two recurring themes in a broad conversation about the societal impact of AI. These concerns arise from the need for huge amounts of data to train deep neural networks. A promise of Generalized Few-shot Object Detection (G-FSOD), a learning paradigm in AI, is to alleviate the need for collecting abundant training samples of novel classes we wish to detect by leveraging prior knowledge from old classes (i.e., base classes). G-FSOD strives to learn these novel classes while alleviating catastrophic forgetting of the base classes. However, existing approaches assume that the base images are accessible, an assumption that does not hold when sharing and storing data is problematic. In this work, we propose the first data-free knowledge distillation (DFKD) approach for G-FSOD that leverages the statistics of the region of interest (RoI) features from the base model to forge instance-level features without accessing the base images. Our contribution is three-fold: (1) we design a standalone lightweight generator with (2) class-wise heads (3) to generate and replay diverse instance-level base features to the RoI head while finetuning on the novel data. This stands in contrast to standard DFKD approaches in image classification, which invert the entire network to generate base images. Moreover, we make careful design choices in the novel finetuning pipeline to regularize the model. We show that our approach can dramatically reduce the base memory requirements, all while setting a new standard for G-FSOD on the challenging MS-COCO and PASCAL-VOC benchmarks.

Karim Guirguis, Mohamed Abdelsamad, George Eskandar et al.

Recent object detection models require large amounts of annotated data for training a new classes of objects. Few-shot object detection (FSOD) aims to address this problem by learning novel classes given only a few samples. While competitive results have been achieved using two-stage FSOD detectors, typically one-stage FSODs underperform compared to them. We make the observation that the large gap in performance between two-stage and one-stage FSODs are mainly due to their weak discriminability, which is explained by a small post-fusion receptive field and a small number of foreground samples in the loss function. To address these limitations, we propose the Few-shot RetinaNet (FSRN) that consists of: a multi-way support training strategy to augment the number of foreground samples for dense meta-detectors, an early multi-level feature fusion providing a wide receptive field that covers the whole anchor area and two augmentation techniques on query and source images to enhance transferability. Extensive experiments show that the proposed approach addresses the limitations and boosts both discriminability and transferability. FSRN is almost two times faster than two-stage FSODs while remaining competitive in accuracy, and it outperforms the state-of-the-art of one-stage meta-detectors and also some two-stage FSODs on the MS-COCO and PASCAL VOC benchmarks.

Karim Guirguis, Ahmed Hendawy, George Eskandar et al.

Few-shot object detection (FSOD) seeks to detect novel categories with limited data by leveraging prior knowledge from abundant base data. Generalized few-shot object detection (G-FSOD) aims to tackle FSOD without forgetting previously seen base classes and, thus, accounts for a more realistic scenario, where both classes are encountered during test time. While current FSOD methods suffer from catastrophic forgetting, G-FSOD addresses this limitation yet exhibits a performance drop on novel tasks compared to the state-of-the-art FSOD. In this work, we propose a constraint-based finetuning approach (CFA) to alleviate catastrophic forgetting, while achieving competitive results on the novel task without increasing the model capacity. CFA adapts a continual learning method, namely Average Gradient Episodic Memory (A-GEM) to G-FSOD. Specifically, more constraints on the gradient search strategy are imposed from which a new gradient update rule is derived, allowing for better knowledge exchange between base and novel classes. To evaluate our method, we conduct extensive experiments on MS-COCO and PASCAL-VOC datasets. Our method outperforms current FSOD and G-FSOD approaches on the novel task with minor degeneration on the base task. Moreover, CFA is orthogonal to FSOD approaches and operates as a plug-and-play module without increasing the model capacity or inference time.

Zeyun Zhong, Manuel Martin, Frederik Diederichs et al.

This report presents a novel Mamba-based encoder-decoder architecture, QueryMamba, featuring an integrated verb-noun interaction module that utilizes a statistical verb-noun co-occurrence matrix to enhance video action forecasting. This architecture not only predicts verbs and nouns likely to occur based on historical data but also considers their joint occurrence to improve forecast accuracy. The efficacy of this approach is substantiated by experimental results, with the method achieving second place in the Ego4D LTA challenge and ranking first in noun prediction accuracy.

Karim Guirguis, George Eskandar, Matthias Kayser et al.

Few-shot object detection (FSOD) has thrived in recent years to learn novel object classes with limited data by transferring knowledge gained on abundant base classes. FSOD approaches commonly assume that both the scarcely provided examples of novel classes and test-time data belong to the same domain. However, this assumption does not hold in various industrial and robotics applications, where a model can learn novel classes from a source domain while inferring on classes from a target domain. In this work, we address the task of zero-shot domain adaptation, also known as domain generalization, for FSOD. Specifically, we assume that neither images nor labels of the novel classes in the target domain are available during training. Our approach for solving the domain gap is two-fold. First, we leverage a meta-training paradigm, where we learn the domain shift on the base classes, then transfer the domain knowledge to the novel classes. Second, we propose various data augmentations techniques on the few shots of novel classes to account for all possible domain-specific information. To constraint the network into encoding domain-agnostic class-specific representations only, a contrastive loss is proposed to maximize the mutual information between foreground proposals and class embeddings and reduce the network's bias to the background information from target domain. Our experiments on the T-LESS, PASCAL-VOC, and ExDark datasets show that the proposed approach succeeds in alleviating the domain gap considerably without utilizing labels or images of novel categories from the target domain.

Anne Sielemann, Valentin Barner, Stefan Wolf et al.

Common approaches to explainable AI (XAI) for deep learning focus on analyzing the importance of input features on the classification task in a given model: saliency methods like SHAP and GradCAM are used to measure the impact of spatial regions of the input image on the classification result. Combined with ground truth information about the location of the object in the input image (e.g., a binary mask), it is determined whether object pixels had a high impact on the classification result, or whether the classification focused on background pixels. The former is considered to be a sign of a healthy classifier, whereas the latter is assumed to suggest overfitting on spurious correlations. A major challenge, however, is that these intuitive interpretations are difficult to test quantitatively, and hence the output of such explanations lacks an explanation itself. One particular reason is that correlations in real-world data are difficult to avoid, and whether they are spurious or legitimate is debatable. Synthetic data in turn can facilitate to actively enable or disable correlations where desired but often lack a sufficient quantification of realism and stochastic properties. [...] Therefore, we systematically generate six synthetic datasets for the task of traffic sign recognition, which differ only in their degree of camera variation and background correlation [...] to quantify the isolated influence of background correlation, different levels of camera variation, and considered traffic sign shapes on the classification performance, as well as background feature importance. [...] Results include a quantification of when and how much background features gain importance to support the classification task based on changes in the training domain [...]. Download: synset.de/datasets/synset-signset-ger/background-effect

Fabian Duerr, Mario Pfaller, Hendrik Weigel et al.

Understanding and interpreting a 3d environment is a key challenge for autonomous vehicles. Semantic segmentation of 3d point clouds combines 3d information with semantics and thereby provides a valuable contribution to this task. In many real-world applications, point clouds are generated by lidar sensors in a consecutive fashion. Working with a time series instead of single and independent frames enables the exploitation of temporal information. We therefore propose a recurrent segmentation architecture (RNN), which takes a single range image frame as input and exploits recursively aggregated temporal information. An alignment strategy, which we call Temporal Memory Alignment, uses ego motion to temporally align the memory between consecutive frames in feature space. A Residual Network and ConvGRU are investigated for the memory update. We demonstrate the benefits of the presented approach on two large-scale datasets and compare it to several stateof-the-art methods. Our approach ranks first on the SemanticKITTI multiple scan benchmark and achieves state-of-the-art performance on the single scan benchmark. In addition, the evaluation shows that the exploitation of temporal information significantly improves segmentation results compared to a single frame approach.