Previous work on multimodal machine translation (MMT) has focused on the way of incorporating vision features into translation but little attention is on the quality of vision models. In this work, we investigate the impact of vision models on MMT. Given the fact that Transformer is becoming popular in computer vision, we experiment with various strong models (such as Vision Transformer) and enhanced features (such as object-detection and image captioning). We develop a selective attention model to study the patch-level contribution of an image in MMT. On detailed probing tasks, we find that stronger vision models are helpful for learning translation from the visual modality. Our results also suggest the need of carefully examining MMT models, especially when current benchmarks are small-scale and biased. Our code could be found at \url{https://github.com/libeineu/fairseq_mmt}.
The effective receptive field of a fully convolutional neural network is an important consideration when designing an architecture, as it defines the portion of the input visible to each convolutional kernel. We propose a neural network module, extending traditional skip connections, called the translated skip connection. Translated skip connections geometrically increase the receptive field of an architecture with negligible impact on both the size of the parameter space and computational complexity. By embedding translated skip connections into a benchmark architecture, we demonstrate that our module matches or outperforms four other approaches to expanding the effective receptive fields of fully convolutional neural networks. We confirm this result across five contemporary image segmentation datasets from disparate domains, including the detection of COVID-19 infection, segmentation of aerial imagery, common object segmentation, and segmentation for self-driving cars.
We introduce Kvasir-VQA, an extended dataset derived from the HyperKvasir and Kvasir-Instrument datasets, augmented with question-and-answer annotations to facilitate advanced machine learning tasks in Gastrointestinal (GI) diagnostics. This dataset comprises 6,500 annotated images spanning various GI tract conditions and surgical instruments, and it supports multiple question types including yes/no, choice, location, and numerical count. The dataset is intended for applications such as image captioning, Visual Question Answering (VQA), text-based generation of synthetic medical images, object detection, and classification. Our experiments demonstrate the dataset's effectiveness in training models for three selected tasks, showcasing significant applications in medical image analysis and diagnostics. We also present evaluation metrics for each task, highlighting the usability and versatility of our dataset. The dataset and supporting artifacts are available at https://datasets.simula.no/kvasir-vqa.
In agricultural image analysis, optimal model performance is keenly pursued for better fulfilling visual recognition tasks (e.g., image classification, segmentation, object detection and localization), in the presence of challenges with biological variability and unstructured environments. Large-scale, balanced and ground-truthed image datasets, however, are often difficult to obtain to fuel the development of advanced, high-performance models. As artificial intelligence through deep learning is impacting analysis and modeling of agricultural images, data augmentation plays a crucial role in boosting model performance while reducing manual efforts for data preparation, by algorithmically expanding training datasets. Beyond traditional data augmentation techniques, generative adversarial network (GAN) invented in 2014 in the computer vision community, provides a suite of novel approaches that can learn good data representations and generate highly realistic samples. Since 2017, there has been a growth of research into GANs for image augmentation or synthesis in agriculture for improved model performance. This paper presents an overview of the evolution of GAN architectures followed by a systematic review of their application to agriculture (https://github.com/Derekabc/GANs-Agriculture), involving various vision tasks for plant health, weeds, fruits, aquaculture, animal farming, plant phenotyping as well as postharvest detection of fruit defects. Challenges and opportunities of GANs are discussed for future research.
Monocular 3D detectors achieve remarkable performance on cars and smaller objects. However, their performance drops on larger objects, leading to fatal accidents. Some attribute the failures to training data scarcity or their receptive field requirements of large objects. In this paper, we highlight this understudied problem of generalization to large objects. We find that modern frontal detectors struggle to generalize to large objects even on nearly balanced datasets. We argue that the cause of failure is the sensitivity of depth regression losses to noise of larger objects. To bridge this gap, we comprehensively investigate regression and dice losses, examining their robustness under varying error levels and object sizes. We mathematically prove that the dice loss leads to superior noise-robustness and model convergence for large objects compared to regression losses for a simplified case. Leveraging our theoretical insights, we propose SeaBird (Segmentation in Bird's View) as the first step towards generalizing to large objects. SeaBird effectively integrates BEV segmentation on foreground objects for 3D detection, with the segmentation head trained with the dice loss. SeaBird achieves SoTA results on the KITTI-360 leaderboard and improves existing detectors on the nuScenes leaderboard, particularly for large objects. Code and models at https://github.com/abhi1kumar/SeaBird
Spiking Neural Networks (SNN) exhibit higher energy efficiency compared to Artificial Neural Networks (ANN) due to their unique spike-driven mechanism. Additionally, SNN possess a crucial characteristic, namely the ability to process spatio-temporal information. However, this ability is constrained by both internal and external factors in practical applications, thereby affecting the performance of SNN. Firstly, the internal issue of SNN lies in the inherent limitations of their network structure and neuronal model, which result in the network adopting a unified processing approach for information of different temporal dimensions when processing input data containing complex temporal information. Secondly, the external issue of SNN stems from the direct encoding method commonly adopted by directly trained SNN, which uses the same feature map for input at each time step, failing to fully exploit the spatio-temporal characteristics of SNN. To address these issues, this paper proposes an Unconstrained Leaky Integrate-and-Fire (ULIF) neuronal model that allows for learning different membrane potential parameters at different time steps, thereby enhancing SNN' ability to process information of different temporal dimensions. Additionally, this paper presents a hybrid encoding scheme aimed at solving the problem of direct encoding lacking temporal dimension information. Experimental results demonstrate that the proposed methods effectively improve the overall performance of SNN in object detection and object recognition tasks. related code is available at https://github.com/hhx0320/ASNN.
We investigate the design aspects of feature distillation methods achieving network compression and propose a novel feature distillation method in which the distillation loss is designed to make a synergy among various aspects: teacher transform, student transform, distillation feature position and distance function. Our proposed distillation loss includes a feature transform with a newly designed margin ReLU, a new distillation feature position, and a partial L2 distance function to skip redundant information giving adverse effects to the compression of student. In ImageNet, our proposed method achieves 21.65% of top-1 error with ResNet50, which outperforms the performance of the teacher network, ResNet152. Our proposed method is evaluated on various tasks such as image classification, object detection and semantic segmentation and achieves a significant performance improvement in all tasks. The code is available at https://sites.google.com/view/byeongho-heo/overhaul
Brain tumor segmentation is one of the most challenging problems in medical image analysis. The goal of brain tumor segmentation is to generate accurate delineation of brain tumor regions. In recent years, deep learning methods have shown promising performance in solving various computer vision problems, such as image classification, object detection and semantic segmentation. A number of deep learning based methods have been applied to brain tumor segmentation and achieved promising results. Considering the remarkable breakthroughs made by state-of-the-art technologies, we use this survey to provide a comprehensive study of recently developed deep learning based brain tumor segmentation techniques. More than 100 scientific papers are selected and discussed in this survey, extensively covering technical aspects such as network architecture design, segmentation under imbalanced conditions, and multi-modality processes. We also provide insightful discussions for future development directions.
Humans can naturally and effectively find salient regions in complex scenes. Motivated by this observation, attention mechanisms were introduced into computer vision with the aim of imitating this aspect of the human visual system. Such an attention mechanism can be regarded as a dynamic weight adjustment process based on features of the input image. Attention mechanisms have achieved great success in many visual tasks, including image classification, object detection, semantic segmentation, video understanding, image generation, 3D vision, multi-modal tasks and self-supervised learning. In this survey, we provide a comprehensive review of various attention mechanisms in computer vision and categorize them according to approach, such as channel attention, spatial attention, temporal attention and branch attention; a related repository https://github.com/MenghaoGuo/Awesome-Vision-Attentions is dedicated to collecting related work. We also suggest future directions for attention mechanism research.
Spiking neural networks (SNNs) operating with asynchronous discrete events show higher energy efficiency with sparse computation. A popular approach for implementing deep SNNs is ANN-SNN conversion combining both efficient training of ANNs and efficient inference of SNNs. However, the accuracy loss is usually non-negligible, especially under a few time steps, which restricts the applications of SNN on latency-sensitive edge devices greatly. In this paper, we first identify that such performance degradation stems from the misrepresentation of the negative or overflow residual membrane potential in SNNs. Inspired by this, we decompose the conversion error into three parts: quantization error, clipping error, and residual membrane potential representation error. With such insights, we propose a two-stage conversion algorithm to minimize those errors respectively. Besides, We show each stage achieves significant performance gains in a complementary manner. By evaluating on challenging datasets including CIFAR-10, CIFAR- 100 and ImageNet, the proposed method demonstrates the state-of-the-art performance in terms of accuracy, latency and energy preservation. Furthermore, our method is evaluated using a more challenging object detection task, revealing notable gains in regression performance under ultra-low latency when compared to existing spike-based detection algorithms. Codes are available at https://github.com/Windere/snn-cvt-dual-phase.
In this paper, we focus on the problem of feature learning in the presence of scale imbalance for 6-DoF grasp detection and propose a novel approach to especially address the difficulty in dealing with small-scale samples. A Multi-scale Cylinder Grouping (MsCG) module is presented to enhance local geometry representation by combining multi-scale cylinder features and global context. Moreover, a Scale Balanced Learning (SBL) loss and an Object Balanced Sampling (OBS) strategy are designed, where SBL enlarges the gradients of the samples whose scales are in low frequency by apriori weights while OBS captures more points on small-scale objects with the help of an auxiliary segmentation network. They alleviate the influence of the uneven distribution of grasp scales in training and inference respectively. In addition, Noisy-clean Mix (NcM) data augmentation is introduced to facilitate training, aiming to bridge the domain gap between synthetic and raw scenes in an efficient way by generating more data which mix them into single ones at instance-level. Extensive experiments are conducted on the GraspNet-1Billion benchmark and competitive results are reached with significant gains on small-scale cases. Besides, the performance of real-world grasping highlights its generalization ability. Our code is available at https://github.com/mahaoxiang822/Scale-Balanced-Grasp.
Salient object detection (SOD) plays a critical role in vision-driven measurement systems (VMS), facilitating the detection and segmentation of key visual elements in an image. However, adverse imaging conditions such as haze during the day, low light, and haze at night severely degrade image quality, and complicating the SOD process. To address these challenges, we propose a multi-task-oriented nighttime haze imaging enhancer (MToIE), which integrates three tasks: daytime dehazing, low-light enhancement, and nighttime dehazing. The MToIE incorporates two key innovative components: First, the network employs a task-oriented node learning mechanism to handle three specific degradation types: day-time haze, low light, and night-time haze conditions, with an embedded self-attention module enhancing its performance in nighttime imaging. In addition, multi-receptive field enhancement module that efficiently extracts multi-scale features through three parallel depthwise separable convolution branches with different dilation rates, capturing comprehensive spatial information with minimal computational overhead. To ensure optimal image reconstruction quality and visual characteristics, we suggest a hybrid loss function. Extensive experiments on different types of weather/imaging conditions illustrate that MToIE surpasses existing methods, significantly enhancing the accuracy and reliability of vision systems across diverse imaging scenarios. The code is available at https://github.com/Ai-Chen-Lab/MToIE.
Fine-grained fashion retrieval searches for items that share a similar attribute with the query image. Most existing methods use a pre-trained feature extractor (e.g., ResNet 50) to capture image representations. However, a pre-trained feature backbone is typically trained for image classification and object detection, which are fundamentally different tasks from fine-grained fashion retrieval. Therefore, existing methods suffer from a feature gap problem when directly using the pre-trained backbone for fine-tuning. To solve this problem, we introduce an attribute-guided multi-level attention network (AG-MAN). Specifically, we first enhance the pre-trained feature extractor to capture multi-level image embedding, thereby enriching the low-level features within these representations. Then, we propose a classification scheme where images with the same attribute, albeit with different values, are categorized into the same class. This can further alleviate the feature gap problem by perturbing object-centric feature learning. Moreover, we propose an improved attribute-guided attention module for extracting more accurate attribute-specific representations. Our model consistently outperforms existing attention based methods when assessed on the FashionAI (62.8788% in MAP), DeepFashion (8.9804% in MAP), and Zappos50k datasets (93.32% in Prediction accuracy). Especially, ours improves the most typical ASENet_V2 model by 2.12%, 0.31%, and 0.78% points in FashionAI, DeepFashion, and Zappos50k datasets, respectively. The source code is available in https://github.com/Dr-LingXiao/AG-MAN.
Remarkable progress has been made in recent years in the fields of vision, language, and robotics. We now have vision models capable of recognizing objects based on language queries, navigation systems that can effectively control mobile systems, and grasping models that can handle a wide range of objects. Despite these advancements, general-purpose applications of robotics still lag behind, even though they rely on these fundamental capabilities of recognition, navigation, and grasping. In this paper, we adopt a systems-first approach to develop a new Open Knowledge-based robotics framework called OK-Robot. By combining Vision-Language Models (VLMs) for object detection, navigation primitives for movement, and grasping primitives for object manipulation, OK-Robot offers a integrated solution for pick-and-drop operations without requiring any training. To evaluate its performance, we run OK-Robot in 10 real-world home environments. The results demonstrate that OK-Robot achieves a 58.5% success rate in open-ended pick-and-drop tasks, representing a new state-of-the-art in Open Vocabulary Mobile Manipulation (OVMM) with nearly 1.8x the performance of prior work. On cleaner, uncluttered environments, OK-Robot's performance increases to 82%. However, the most important insight gained from OK-Robot is the critical role of nuanced details when combining Open Knowledge systems like VLMs with robotic modules. Videos of our experiments and code are available on our website: https://ok-robot.github.io
Perception and prediction modules are critical components of autonomous driving systems, enabling vehicles to navigate safely through complex environments. The perception module is responsible for perceiving the environment, including static and dynamic objects, while the prediction module is responsible for predicting the future behavior of these objects. These modules are typically divided into three tasks: object detection, object tracking, and motion prediction. Traditionally, these tasks are developed and optimized independently, with outputs passed sequentially from one to the next. However, this approach has significant limitations: computational resources are not shared across tasks, the lack of joint optimization can amplify errors as they propagate throughout the pipeline, and uncertainty is rarely propagated between modules, resulting in significant information loss. To address these challenges, the joint perception and prediction paradigm has emerged, integrating perception and prediction into a unified model through multi-task learning. This strategy not only overcomes the limitations of previous methods, but also enables the three tasks to have direct access to raw sensor data, allowing richer and more nuanced environmental interpretations. This paper presents the first comprehensive survey of joint perception and prediction for autonomous driving. We propose a taxonomy that categorizes approaches based on input representation, scene context modeling, and output representation, highlighting their contributions and limitations. Additionally, we present a qualitative analysis and quantitative comparison of existing methods. Finally, we discuss future research directions based on identified gaps in the state-of-the-art.
Instance segmentation with neural networks is an essential task in environment perception. In many works, it has been observed that neural networks can predict false positive instances with high confidence values and true positives with low ones. Thus, it is important to accurately model the uncertainties of neural networks in order to prevent safety issues and foster interpretability. In applications such as automated driving, the reliability of neural networks is of highest interest. In this paper, we present a time-dynamic approach to model uncertainties of instance segmentation networks and apply this to the detection of false positives as well as the estimation of prediction quality. The availability of image sequences in online applications allows for tracking instances over multiple frames. Based on an instances history of shape and uncertainty information, we construct temporal instance-wise aggregated metrics. The latter are used as input to post-processing models that estimate the prediction quality in terms of instance-wise intersection over union. The proposed method only requires a readily trained neural network (that may operate on single frames) and video sequence input. In our experiments, we further demonstrate the use of the proposed method by replacing the traditional score value from object detection and thereby improving the overall performance of the instance segmentation network.
Event cameras are bio-inspired sensors that respond to per-pixel brightness changes in the form of asynchronous and sparse "events". Recently, pattern recognition algorithms, such as learning-based methods, have made significant progress with event cameras by converting events into synchronous dense, image-like representations and applying traditional machine learning methods developed for standard cameras. However, these approaches discard the spatial and temporal sparsity inherent in event data at the cost of higher computational complexity and latency. In this work, we present a general framework for converting models trained on synchronous image-like event representations into asynchronous models with identical output, thus directly leveraging the intrinsic asynchronous and sparse nature of the event data. We show both theoretically and experimentally that this drastically reduces the computational complexity and latency of high-capacity, synchronous neural networks without sacrificing accuracy. In addition, our framework has several desirable characteristics: (i) it exploits spatio-temporal sparsity of events explicitly, (ii) it is agnostic to the event representation, network architecture, and task, and (iii) it does not require any train-time change, since it is compatible with the standard neural networks' training process. We thoroughly validate the proposed framework on two computer vision tasks: object detection and object recognition. In these tasks, we reduce the computational complexity up to 20 times with respect to high-latency neural networks. At the same time, we outperform state-of-the-art asynchronous approaches up to 24% in prediction accuracy.
Current deep neural networks (DNNs) for autonomous driving computer vision are typically trained on specific datasets that only involve a single type of data and urban scenes. Consequently, these models struggle to handle new objects, noise, nighttime conditions, and diverse scenarios, which is essential for safety-critical applications. Despite ongoing efforts to enhance the resilience of computer vision DNNs, progress has been sluggish, partly due to the absence of benchmarks featuring multiple modalities. We introduce a novel and versatile dataset named InfraParis that supports multiple tasks across three modalities: RGB, depth, and infrared. We assess various state-of-the-art baseline techniques, encompassing models for the tasks of semantic segmentation, object detection, and depth estimation. More visualizations and the download link for InfraParis are available at \href{https://ensta-u2is.github.io/infraParis/}{https://ensta-u2is.github.io/infraParis/}.
In this paper, we describe how the electronic rolling shutter in CMOS image sensors can be exploited using a bright, modulated light source (e.g., an inexpensive, off-the-shelf laser), to inject fine-grained image disruptions. We demonstrate the attack on seven different CMOS cameras, ranging from cheap IoT to semi-professional surveillance cameras, to highlight the wide applicability of the rolling shutter attack. We model the fundamental factors affecting a rolling shutter attack in an uncontrolled setting. We then perform an exhaustive evaluation of the attack's effect on the task of object detection, investigating the effect of attack parameters. We validate our model against empirical data collected on two separate cameras, showing that by simply using information from the camera's datasheet the adversary can accurately predict the injected distortion size and optimize their attack accordingly. We find that an adversary can hide up to 75% of objects perceived by state-of-the-art detectors by selecting appropriate attack parameters. We also investigate the stealthiness of the attack in comparison to a na\"{i}ve camera blinding attack, showing that common image distortion metrics can not detect the attack presence. Therefore, we present a new, accurate and lightweight enhancement to the backbone network of an object detector to recognize rolling shutter attacks. Overall, our results indicate that rolling shutter attacks can substantially reduce the performance and reliability of vision-based intelligent systems.
Understanding relations between objects is crucial for understanding the semantics of a visual scene. It is also an essential step in order to bridge visual and language models. However, current state-of-the-art computer vision models still lack the ability to perform spatial reasoning well. Existing datasets mostly cover a relatively small number of spatial relations, all of which are static relations that do not intrinsically involve motion. In this paper, we propose the Spatial and Temporal Understanding of Prepositions Dataset (STUPD) -- a large-scale video dataset for understanding static and dynamic spatial relationships derived from prepositions of the English language. The dataset contains 150K visual depictions (videos and images), consisting of 30 distinct spatial prepositional senses, in the form of object interaction simulations generated synthetically using Unity3D. In addition to spatial relations, we also propose 50K visual depictions across 10 temporal relations, consisting of videos depicting event/time-point interactions. To our knowledge, no dataset exists that represents temporal relations through visual settings. In this dataset, we also provide 3D information about object interactions such as frame-wise coordinates, and descriptions of the objects used. The goal of this synthetic dataset is to help models perform better in visual relationship detection in real-world settings. We demonstrate an increase in the performance of various models over 2 real-world datasets (ImageNet-VidVRD and Spatial Senses) when pretrained on the STUPD dataset, in comparison to other pretraining datasets.