skip to main content

Title: A Fast and Accurate One-Stage Approach to Visual Grounding
We propose a simple, fast, and accurate one-stage approach to visual grounding, inspired by the following insight. The performances of existing propose-and-rank twostage methods are capped by the quality of the region candidates they propose in the first stage — if none of the candidates could cover the ground truth region, there is no hope in the second stage to rank the right region to the top. To avoid this caveat, we propose a one-stage model that enables end-to-end joint optimization. The main idea is as straightforward as fusing a text query’s embedding into the YOLOv3 object detector, augmented by spatial features so as to account for spatial mentions in the query. Despite being simple, this one-stage approach shows great potential in terms of both accuracy and speed for both phrase localization and referring expression comprehension, according to our experiments. Given these results along with careful investigations into some popular region proposals, we advocate for visual grounding a paradigm shift from the conventional two-stage methods to the one-stage framework.
; ; ; ; ;
Award ID(s):
1813709 1722847
Publication Date:
Journal Name:
International Conference on Computer Vision
Sponsoring Org:
National Science Foundation
More Like this
  1. Finding diagrams that contain a specific part or a similar part is important in many engineering tasks. In this search task, the query part is expected to match only a small region in a complex image.This paper investigates several local matching networks that explicitly model local region-to-region similarities. Deep convolutional neural networks extract local features and model local matching patterns. Spatial convolution is employed to cross-match local regions at different scale levels, addressing cases where the target part appears at a different scale, position, and/or angle. A gating network automatically learns region importance, removing noise from sparse areas and visualmore »metadata in engineering diagrams. Experimental results show that local matching approaches are more effective for engineering diagram search than global matching approaches. Suppressing unimportant regions via the gating net-work enhances accuracy. Matching across different scales via spatial convolution substantially improves robustness to scale and rotation changes. A pipelined architecture efficiently searches a large collection of diagrams by using a simple local matching network to identify a small set of candidate images and a more sophisticated network with convolutional cross-scale matching to re-rank candidates.« less
  2. Recently, the region proposal networks (RPN) have been combined with the Siamese network for tracking, and shown excellent accuracy with high efficiency. Nevertheless, previously proposed one-stage Siamese-RPN trackers degenerate in presence of similar distractors and large scale variation. Addressing these issues, we propose a multi-stage tracking framework, Siamese Cascaded RPN (C-RPN), which consists of a sequence of RPNs cascaded from deep high-level to shallow low-level layers in a Siamese network. Compared to previous solutions, C-RPN has several advantages: (1) Each RPN is trained using the outputs of RPN in the previous stage. Such process stimulates hard negative sampling, resulting inmore »more balanced training samples. Consequently, the RPNs are sequentially more discriminative in distinguishing difficult background (i.e., similar distractors). (2) Multi-level features are fully leveraged through a novel feature transfer block (FTB) for each RPN, further improving the discriminability of C-RPN using both high-level semantic and low-level spatial information. (3) With multiple steps of regressions, C-RPN progressively refines the location and shape of the target in each RPN with adjusted anchor boxes in the previous stage, which makes localization more accurate. C-RPN is trained end-to-end with the multi-task loss function. In inference, C-RPN is deployed as it is, without any temporal adaption, for real-time tracking. In extensive experiments on OTB-2013, OTB-2015, VOT- 2016, VOT-2017, LaSOT and TrackingNet, C-RPN consistently achieves state-of-the-art results and runs in real-time.« less
  3. In most environments, the visual system is confronted with many relevant objects simultaneously. That is especially true during reading. However, behavioral data demonstrate that a serial bottleneck prevents recognition of more than one word at a time. We used fMRI to investigate how parallel spatial channels of visual processing converge into a serial bottleneck for word recognition. Participants viewed pairs of words presented simultaneously. We found that retinotopic cortex processed the two words in parallel spatial channels, one in each contralateral hemisphere. Responses were higher for attended than for ignored words but were not reduced when attention was divided. Wemore »then analyzed two word-selective regions along the occipitotemporal sulcus (OTS) of both hemispheres (subregions of the visual word form area, VWFA). Unlike retinotopic regions, each word-selective region responded to words on both sides of fixation. Nonetheless, a single region in the left hemisphere (posterior OTS) contained spatial channels for both hemifields that were independently modulated by selective attention. Thus, the left posterior VWFA supports parallel processing of multiple words. In contrast, activity in a more anterior word-selective region in the left hemisphere (mid OTS) was consistent with a single channel, showing (i) limited spatial selectivity, (ii) no effect of spatial attention on mean response amplitudes, and (iii) sensitivity to lexical properties of only one attended word. Therefore, the visual system can process two words in parallel up to a late stage in the ventral stream. The transition to a single channel is consistent with the observed bottleneck in behavior.

    « less
  4. Visual features and representation learning strategies experienced huge advances in the previous decade, mainly supported by deep learning approaches. However, retrieval tasks are still performed mainly based on traditional pairwise dissimilarity measures, while the learned representations lie on high dimensional manifolds. With the aim of going beyond pairwise analysis, post-processing methods have been proposed to replace pairwise measures by globally defined measures, capable of analyzing collections in terms of the underlying data manifold. The most representative approaches are diffusion and ranked-based methods. While the diffusion approaches can be computationally expensive, the rank-based methods lack theoretical background. In this paper, wemore »propose an efficient Rank-based Diffusion Process which combines both approaches and avoids the drawbacks of each one. The obtained method is capable of efficiently approximating a diffusion process by exploiting rank-based information, while assuring its convergence. The algorithm exhibits very low asymptotic complexity and can be computed regionally, being suitable to outside of dataset queries. An experimental evaluation conducted for image retrieval and person re-ID tasks on diverse datasets demonstrates the effectiveness of the proposed approach with results comparable to the state-of-the-art.« less
  5. Understanding spatial relations (e.g., laptop on table) in visual input is important for both humans and robots. Existing datasets are insufficient as they lack large-scale, high-quality 3D ground truth information, which is critical for learning spatial relations. In this paper, we fill this gap by constructing Rel3D: the first large-scale, human-annotated dataset for grounding spatial relations in 3D. Rel3D enables quantifying the effectiveness of 3D information in predicting spatial relations on large-scale human data. Moreover, we propose minimally contrastive data collection---a novel crowdsourcing method for reducing dataset bias. The 3D scenes in our dataset come in minimally contrastive pairs: twomore »scenes in a pair are almost identical, but a spatial relation holds in one and fails in the other. We empirically validate that minimally contrastive examples can diagnose issues with current relation detection models as well as lead to sample-efficient training. Code and data are available at« less