This work proposes a self-supervised neuromorphic processor using high-dimensional representations for cognitive map navigation. By employing the Cognitive Map Learner (CML), it enables agents to explore and understand diverse environments online through random walks. To enhance path planning, the agent’s actions and observations are embedded into high-dimensional state spaces. This embedding creates a sense of direction, simplifying navigation into a retrieval process within an Associative Memory (AM). We design an energy-efficient processor that features a scalable multi-core hardware architecture with precision flexibility, combined with an on-chip random walk training engine. To balance the precision of the model with hardware overhead, two hardware-software co-design strategies are proposed. The first is a Content-Addressable Memory (CAM)-based approach for AM access, which reduces the number of memory access by up to 25%. The second involves high-dimensional matrix sparsity optimizations, reducing computation operations to less than 8%. We simulate this processor by a 40-nm CMOS technology, which has 2.88 mm2core area with 15.8 mW power at a frequency of 140 MHz. Compared to previous processors, our experiments show that the proposed processor achieves outstanding success rates of 99.9%, 96%, and 98.7% on 100 2D nodes, 125 3D nodes, and 25 abstract map nodes with obstacles, respectively. In terms of energy efficiency, it delivers a path planning result of 28 nJ/node and 35 nJ/node in 2D and 3D maps, offering a 1.2x to 2.9x improvement over the state-of-the-art.

Indoor 3D domain adaptation for semantic segmentation is an understudied task. The first unsupervised sim-to-real benchmark was only proposed recently. Existing methods try to modify the source domain data by simulating the occlusion and noise pattern of the target domain. However, this methodology unrealistically demands a clear definition of the real-world data patterns, and is highly dependent on the simulation quality. In this paper, we propose a novel adaptation framework via Context-aware Augmentation and Consistency Enforcement (CACE). Our CACE framework consists of two modules, a space and context-aware augmentation module that is invariant of target data pattern and domain gaps, and a carefully designed self-supervision module that maximizes the utility of the augmented data. Our CACE surpasses the state-of-the-art method by over 6% on the indoor 3D sim-to-real benchmark$3D-FRONT\rightarrow ScanNet$.

In this paper, we propose a novel learning framework for autonomous systems that uses a small amount of “auxiliary information” that complements the learning of the main modality, called “small-shot auxiliary modality distillation network (AMD-S-Net)”. The AMD-S-Net contains a two-stream framework design that can fully extract information from different types of data (i.e., paired/unpaired multi-modality data) to distill knowledge more effectively. We also propose a novel training paradigm based on the “reset operation” that enables the teacher to explore the local loss landscape near the student domain iteratively, providing local landscape information and potential directions to discover better solutions by the student, thus achieving higher learning performance. Our experiments show that AMD-S-Net and our training paradigm outperform other SOTA methods by up to 12.7% and 18.1% improvement in autonomous steering, respectively.

Semi-supervised domain adaptation (SSDA) aims to adapt models trained from a labeled source domain to a different but related target domain, from which unlabeled data and a small set of labeled data are provided. Current methods that treat source and target supervision without distinction overlook their inherent discrepancy, resulting in a source-dominated model that has not effectively use the target supervision. In this paper, we argue that the labeled target data needs to be distinguished for effective SSDA, and propose to explicitly decompose the SSDA task into two sub-tasks: a semi-supervised learning (SSL) task in the target domain and an unsupervised domain adaptation (UDA) task across domains. By doing so, the two sub-tasks can better leverage the corresponding supervision and thus yield very different classifiers. To integrate the strengths of the two classifiers, we apply the well established co-training framework, in which the two classifiers exchange their high confident predictions to iteratively "teach each other" so that both classifiers can excel in the target domain. We call our approach Deep Co-training with Task decomposition (DeCoTa). DeCoTa requires no adversarial training and is easy to implement. Moreover, DeCoTa is well founded on the theoretical condition of when co-training would succeed. As a result, DeCoTa achieves state-of-the-art results on several SSDA datasets, outperforming the prior art by a notable 4% margin on DomainNet. Code is available at https://github.com/LoyoYang/DeCoTa.

Fertility refers to the ability of animals to maintain reproductive function and give birth to offspring, which is an important indicator to measure the productivity of animals. Fertility is affected by many factors, among which environmental factors may also play key roles. During the past years, substantial research studies have been conducted to detect the factors related to fecundity, including genetic factors and environmental factors. However, the identified genes associated with fertility from countless previous studies are randomly dispersed in the literature, whereas some other novel fertility-related genes are needed to detect from omics-based datasets. Here, we constructed a fertility index factor database FifBase based on manually curated published literature and RNA-Seq datasets. During the construction of the literature group, we obtained 3301 articles related to fecundity for 13 species from PubMed, involving 2823 genes, which are related to 75 fecundity indicators or 47 environmental factors. Eventually, 1558 genes associated with fertility were filtered in 10 species, of which 1088 and 470 were from RNA-Seq datasets and text mining data, respectively, involving 2910 fertility-gene pairs and 58 fertility-environmental factors. All these data were cataloged into FifBase (http://www.nwsuaflmz.com/FifBase/), where the fertility-related factor information, including gene annotation and environmental factors, can be browsed, retrieved and downloaded with the user-friendly interface.