We thank the reviewers for their valuable feedback and comments. R3 & R5 point out that parts of some modules are based on prior work. Novelty is also recognized by R1 ("clear algorithmic innovation") and R2 ("adds several new features"). All reviewers have appreciated the real-world experiments in the submission. R1 & R5 have suggested there should be more emphasis on real-world experiments.

Dogs have a unique evolutionary relationship with humans and serve many important roles e.g. search and rescue, blind assistance, emotional support. However, few datasets exist to categorize visual features and objects available to dogs, as well as how dogs direct their visual attention within their environment. We collect and study a dataset with over 11,698 gazes to categorize the objects available to be gazed at by 11 dogs in everyday outdoor environments i.e. a walk around a college campus and urban area. We explore the availability of these object categories and the visual attention of dogs over these categories using a head mounted eye tracking apparatus. A small portion (approx. 600 images or < 20% of total dataset) of the collected data is used to fine tune a MaskRCNN for the novel image domain to segment objects present in the scene, enabling further statistical analysis on the visual gaze tendencies of dogs. The MaskRCNN, with eye tracking apparatus, serves as an end to end model for automatically classifying the visual fixations of dogs. The fine tuned MaskRCNN performs far better than chance. There are few individual differences between the 11 dogs and we observe greater visual fixations on buses, plants, pavement, and construction equipment. This work takes a step towards understanding visual behavior of dogs and their interaction with the physical world.

Minimally invasive surgeries and related applications demand surgical tool classification and segmentation at the instance level. Surgical tools are similar in appearance and are long, thin, and handled at an angle. The fine-tuning of state-of-the-art (SOTA) instance segmentation models trained on natural images for instrument segmentation has difficulty discriminating instrument classes. Our research demonstrates that while the bounding box and segmentation mask are often accurate, the classification head mis-classifies the class label of the surgical instrument. We present a new neural network framework that adds a classification module as a new stage to existing instance segmentation models. This module specializes in improving the classification of instrument masks generated by the existing model. The module comprises multi-scale mask attention, which attends to the instrument region and masks the distracting background features. We propose training our classifier module using metric learning with arc loss to handle low inter-class variance of surgical instruments. We conduct exhaustive experiments on the benchmark datasets EndoVis2017 and EndoVis2018. We demonstrate that our method outperforms all (more than 18) SOTA methods compared with, and improves the SOTA performance by at least 12 points (20%) on the EndoVis2017 benchmark challenge and generalizes effectively across the datasets.

An interactive instruction following task has been proposed as a benchmark for learning to map natural language instructions and first-person vision into sequences of actions to interact with objects in a 3D simulated environment. We find that an existing end-to-end neural model for this task is not robust to variations of objects and language instructions. We assume that this problem is due to the high sensitiveness of neural feature extraction to small changes in vision and language inputs. To mitigate this problem, we propose a neuro-symbolic approach that performs reasoning over high-level symbolic representations that are robust to small changes in raw inputs. Our experiments on the ALFRED dataset show that our approach significantly outperforms the existing model by 18, 52, and 73 points in the success rate on the ToggleObject, PickupObject, and SliceObject subtasks in unseen environments respectively.

Humans learn to better understand the world by moving around their environment to get more informative viewpoints of the scene. Most methods for 2D visual recognition tasks such as object detection and segmentation treat images of the same scene as individual samples and do not exploit object permanence in multiple views. Generalization to novel scenes and views thus requires additional training with lots of human annotations. In this paper, we propose a self-supervised framework to improve an object detector in unseen scenarios by moving an agent around in a 3D environment and aggregating multi-view RGB-D information. We unproject confident 2D object detections from the pre-trained detector and perform unsupervised 3D segmentation on the point cloud. The segmented 3D objects are then re-projected to all other views to obtain pseudo-labels for fine-tuning. Experiments on both indoor and outdoor datasets show that (1) our framework performs high-quality 3D segmentation from raw RGB-D data and a pre-trained 2D detector; (2) fine-tuning with self-supervision improves the 2D detector significantly where an unseen RGB image is given as input at test time; (3) training a 3D detector with self-supervision outperforms a comparable self-supervised method by a large margin.